Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.9800. Min Act: -0.1700
Data Index: 3169204 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.2613. Min Act: -0.1700
Data Index: 7153724 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.1363. Min Act: -0.1700
Data Index: 290064 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.1050. Min Act: -0.1700
Data Index: 889604 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.0738. Min Act: -0.1700
Data Index: 7666091 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.0738. Min Act: -0.1700
Data Index: 1733667 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.0425. Min Act: -0.1700
Data Index: 7068535 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.0425. Min Act: -0.1700
Data Index: 886617 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.0113. Min Act: -0.1700
Data Index: 6788411 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.0113. Min Act: -0.1700
Data Index: 6255407 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.0113. Min Act: -0.1700
Data Index: 5083327 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9800. Min Range: -6.9800
Max Act: 6.0113. Min Act: -0.1700
Data Index: 7903560 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9800. Min Range: -6.9800
Max Act: 5.9800. Min Act: -0.1700
Data Index: 4331257 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9800. Min Range: -6.9800
Max Act: 5.9488. Min Act: -0.1700
Data Index: 3317020 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9800. Min Range: -6.9800
Max Act: 5.9175. Min Act: -0.1700
Data Index: 1659283 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9800. Min Range: -6.9800
Max Act: 5.8863. Min Act: -0.1700
Data Index: 3538678 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9800. Min Range: -6.9800
Max Act: 5.8863. Min Act: -0.1700
Data Index: 7307980 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9800. Min Range: -6.9800
Max Act: 5.8863. Min Act: -0.1700
Data Index: 5389803 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9800. Min Range: -6.9800
Max Act: 5.8550. Min Act: -0.1700
Data Index: 3707145 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9800. Min Range: -6.9800
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5231606 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19