Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1833 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.4223. Min Act: -0.1700
Data Index: 907300 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.2973. Min Act: -0.1700
Data Index: 3138887 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.2348. Min Act: -0.1700
Data Index: 1532928 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.2661. Min Act: -0.1700
Data Index: 7179721 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.2036. Min Act: -0.1700
Data Index: 7098831 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.2036. Min Act: -0.1700
Data Index: 3953179 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.2036. Min Act: -0.1700
Data Index: 7512153 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1723. Min Act: -0.1700
Data Index: 1463143 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1411. Min Act: -0.1700
Data Index: 698121 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.2036. Min Act: -0.1700
Data Index: 496373 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.2036. Min Act: -0.1700
Data Index: 3235168 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1723. Min Act: -0.1700
Data Index: 6164508 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1411. Min Act: -0.1700
Data Index: 7490272 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1098. Min Act: -0.1700
Data Index: 1453256 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1411. Min Act: -0.1700
Data Index: 2804248 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1411. Min Act: -0.1700
Data Index: 6570487 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1411. Min Act: -0.1700
Data Index: 8516149 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1098. Min Act: -0.1700
Data Index: 5325527 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1098. Min Act: -0.1700
Data Index: 414168 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4223. Min Range: -7.4223
Max Act: 7.1098. Min Act: -0.1700
Data Index: 1053170 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19