Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.4919. Min Act: -0.1700
Data Index: 3036725 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.3669. Min Act: -0.1700
Data Index: 1817207 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.3981. Min Act: -0.1700
Data Index: 196102 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.3356. Min Act: -0.1700
Data Index: 8419352 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.2731. Min Act: -0.1700
Data Index: 2300504 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.2419. Min Act: -0.1700
Data Index: 7456236 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.2419. Min Act: -0.1700
Data Index: 2209160 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.2106. Min Act: -0.1700
Data Index: 6497965 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1794. Min Act: -0.1700
Data Index: 1387768 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1794. Min Act: -0.1700
Data Index: 6764438 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1481. Min Act: -0.1700
Data Index: 6872738 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1481. Min Act: -0.1700
Data Index: 694000 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1481. Min Act: -0.1700
Data Index: 6927394 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1481. Min Act: -0.1700
Data Index: 3970794 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1481. Min Act: -0.1700
Data Index: 2618960 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1481. Min Act: -0.1700
Data Index: 5651335 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.0856. Min Act: -0.1700
Data Index: 842802 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1168. Min Act: -0.1700
Data Index: 7226463 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1168. Min Act: -0.1700
Data Index: 5407457 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4919. Min Range: -4.4919
Max Act: 4.1168. Min Act: -0.1700
Data Index: 8009646 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19