Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.6976. Min Act: -0.1700
Data Index: 288092 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.6037. Min Act: -0.1700
Data Index: 4727583 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5724. Min Act: -0.1700
Data Index: 6993619 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5411. Min Act: -0.1700
Data Index: 2495326 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5098. Min Act: -0.1700
Data Index: 4605706 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4471. Min Act: -0.1700
Data Index: 1761037 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4471. Min Act: -0.1700
Data Index: 271480 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4314. Min Act: -0.1700
Data Index: 6479468 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4157. Min Act: -0.1700
Data Index: 6242645 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4001. Min Act: -0.1700
Data Index: 5873002 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3687. Min Act: -0.1700
Data Index: 6937094 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3687. Min Act: -0.1700
Data Index: 3064323 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3844. Min Act: -0.1700
Data Index: 3545495 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3844. Min Act: -0.1700
Data Index: 3955288 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3687. Min Act: -0.1700
Data Index: 2943820 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3530. Min Act: -0.1700
Data Index: 337669 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3530. Min Act: -0.1700
Data Index: 1203357 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3373. Min Act: -0.1700
Data Index: 5431879 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3216. Min Act: -0.1700
Data Index: 1590150 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.3373. Min Act: -0.1700
Data Index: 4207587 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19