Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5546 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.5389. Min Act: -0.1700
Data Index: 4456437 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4919. Min Act: -0.1700
Data Index: 3017318 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.5076. Min Act: -0.1700
Data Index: 2696270 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4919. Min Act: -0.1700
Data Index: 672698 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4763. Min Act: -0.1700
Data Index: 3117439 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4763. Min Act: -0.1700
Data Index: 2695913 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4606. Min Act: -0.1700
Data Index: 416472 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4606. Min Act: -0.1700
Data Index: 5028826 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4449. Min Act: -0.1700
Data Index: 4077873 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4293. Min Act: -0.1700
Data Index: 8152032 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4136. Min Act: -0.1700
Data Index: 3674849 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4293. Min Act: -0.1700
Data Index: 6495051 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4293. Min Act: -0.1700
Data Index: 1636002 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4293. Min Act: -0.1700
Data Index: 6195263 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3979. Min Act: -0.1700
Data Index: 74623 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4136. Min Act: -0.1700
Data Index: 6433826 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4136. Min Act: -0.1700
Data Index: 2451381 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3979. Min Act: -0.1700
Data Index: 4653980 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3979. Min Act: -0.1700
Data Index: 6005338 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3979. Min Act: -0.1700
Data Index: 6031125 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19