Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3997 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.9684. Min Act: -0.1700
Data Index: 6397334 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.9372. Min Act: -0.1700
Data Index: 6397326 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.9059. Min Act: -0.1700
Data Index: 6397333 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.9059. Min Act: -0.1700
Data Index: 7655856 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.8121. Min Act: -0.1700
Data Index: 8631210 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7495. Min Act: -0.1700
Data Index: 4913744 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7182. Min Act: -0.1700
Data Index: 5334887 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7495. Min Act: -0.1700
Data Index: 2355291 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7495. Min Act: -0.1700
Data Index: 7846799 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7495. Min Act: -0.1700
Data Index: 8824170 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7182. Min Act: -0.1700
Data Index: 3426412 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7182. Min Act: -0.1700
Data Index: 5098952 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7182. Min Act: -0.1700
Data Index: 1332741 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.6870. Min Act: -0.1700
Data Index: 7773757 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7182. Min Act: -0.1700
Data Index: 1220035 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7182. Min Act: -0.1700
Data Index: 4837332 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.6870. Min Act: -0.1700
Data Index: 4039675 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7182. Min Act: -0.1700
Data Index: 3581446 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7182. Min Act: -0.1700
Data Index: 7744763 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7182. Min Act: -0.1700
Data Index: 5462542 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19