Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.8486. Min Act: -0.1700
Data Index: 8247356 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.8486. Min Act: -0.1700
Data Index: 1040607 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.8228. Min Act: -0.1585
Data Index: 3216583 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.8142. Min Act: -0.1700
Data Index: 3756397 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.8142. Min Act: -0.1700
Data Index: 3273555 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7970. Min Act: -0.1700
Data Index: 3653520 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7970. Min Act: -0.1700
Data Index: 4681394 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7798. Min Act: -0.1700
Data Index: 6657246 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7884. Min Act: -0.1700
Data Index: 516880 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7626. Min Act: -0.1693
Data Index: 3787407 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7539. Min Act: -0.1700
Data Index: 8741913 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7453. Min Act: -0.1696
Data Index: 6695639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7367. Min Act: -0.1700
Data Index: 8723813 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7367. Min Act: -0.1700
Data Index: 326365 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7367. Min Act: -0.1700
Data Index: 8247357 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7367. Min Act: -0.1700
Data Index: 2632001 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7280. Min Act: -0.1700
Data Index: 7507817 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7280. Min Act: -0.1698
Data Index: 5720916 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7280. Min Act: -0.1700
Data Index: 4850463 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8486. Min Range: -1.8486
Max Act: 1.7107. Min Act: -0.1698
Data Index: 3393409 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19