Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.6271. Min Act: -0.1700
Data Index: 7420695 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.5489. Min Act: -0.1700
Data Index: 5616713 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.5489. Min Act: -0.1700
Data Index: 7483428 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.4862. Min Act: -0.1700
Data Index: 6361240 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.4392. Min Act: -0.1700
Data Index: 2576956 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.3922. Min Act: -0.1700
Data Index: 2155600 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.3451. Min Act: -0.1700
Data Index: 7821662 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.3138. Min Act: -0.1700
Data Index: 1304368 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.3294. Min Act: -0.1700
Data Index: 4510080 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.3294. Min Act: -0.1700
Data Index: 2089058 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2981. Min Act: -0.1700
Data Index: 570398 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2824. Min Act: -0.1700
Data Index: 8679587 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2666. Min Act: -0.1700
Data Index: 8269761 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2666. Min Act: -0.1700
Data Index: 576492 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2509. Min Act: -0.1700
Data Index: 7162802 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2509. Min Act: -0.1700
Data Index: 3598161 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2509. Min Act: -0.1700
Data Index: 699028 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2509. Min Act: -0.1700
Data Index: 2741463 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2352. Min Act: -0.1700
Data Index: 3404978 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6271. Min Range: -3.6271
Max Act: 3.2352. Min Act: -0.1700
Data Index: 7340918 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19