Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3714 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.6448. Min Act: -0.1700
Data Index: 6042157 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.4573. Min Act: -0.1700
Data Index: 831899 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.3635. Min Act: -0.1700
Data Index: 6594799 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.3323. Min Act: -0.1700
Data Index: 486614 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.2698. Min Act: -0.1700
Data Index: 1450800 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.2385. Min Act: -0.1700
Data Index: 514161 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.2385. Min Act: -0.1700
Data Index: 5399089 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.2073. Min Act: -0.1700
Data Index: 3408246 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.2073. Min Act: -0.1700
Data Index: 243971 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.2073. Min Act: -0.1700
Data Index: 4781721 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.1760. Min Act: -0.1700
Data Index: 3144142 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.1760. Min Act: -0.1700
Data Index: 6075548 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.1448. Min Act: -0.1700
Data Index: 2955739 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.1448. Min Act: -0.1700
Data Index: 6169057 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.1448. Min Act: -0.1700
Data Index: 5215257 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.1135. Min Act: -0.1700
Data Index: 6208768 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.1135. Min Act: -0.1700
Data Index: 5491659 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.1135. Min Act: -0.1700
Data Index: 1471196 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.1135. Min Act: -0.1700
Data Index: 53039 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6448. Min Range: -5.6448
Max Act: 5.0823. Min Act: -0.1700
Data Index: 3424386 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19