Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3902 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 16.2796. Min Range: -16.2796
Max Act: 16.2796. Min Act: -0.1700
Data Index: 5994304 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.2796. Min Range: -16.2796
Max Act: 16.2796. Min Act: -0.1700
Data Index: 8500773 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.2796. Min Range: -16.2796
Max Act: 16.2796. Min Act: -0.1700
Data Index: 5996704 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.9671. Min Act: -0.1700
Data Index: 4242080 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.9046. Min Act: -0.1700
Data Index: 6718054 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.7171. Min Act: -0.1700
Data Index: 781003 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.6546. Min Act: -0.1700
Data Index: 506326 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.6546. Min Act: -0.1700
Data Index: 4103605 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.5296. Min Act: -0.1700
Data Index: 7495271 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.4046. Min Act: -0.1700
Data Index: 506328 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.4046. Min Act: -0.1700
Data Index: 4574372 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.4046. Min Act: -0.1700
Data Index: 7204632 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.4046. Min Act: -0.1700
Data Index: 3312388 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.4046. Min Act: -0.1700
Data Index: 939837 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.3421. Min Act: -0.1700
Data Index: 1019604 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.3421. Min Act: -0.1700
Data Index: 4412198 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.2796. Min Act: -0.1700
Data Index: 2726301 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.4046. Min Act: -0.1700
Data Index: 4944139 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.3421. Min Act: -0.1699
Data Index: 1766050 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.2796. Min Range: -16.2796
Max Act: 15.2796. Min Act: -0.1700
Data Index: 1515171 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19