Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1163 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.7105. Min Act: -0.1700
Data Index: 4434117 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.6792. Min Act: -0.1700
Data Index: 5217769 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5855. Min Act: -0.1700
Data Index: 1627523 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5855. Min Act: -0.1700
Data Index: 3558929 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5855. Min Act: -0.1700
Data Index: 3669249 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5230. Min Act: -0.1700
Data Index: 6556042 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5230. Min Act: -0.1700
Data Index: 5172577 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4917. Min Act: -0.1700
Data Index: 6577402 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 5316853 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4917. Min Act: -0.1700
Data Index: 3557554 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 7832490 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 1347728 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 7824534 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 6271999 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 2401173 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 313290 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4292. Min Act: -0.1700
Data Index: 7238440 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 6005620 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.3980. Min Act: -0.1700
Data Index: 2674309 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.3980. Min Act: -0.1700
Data Index: 2347038 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19