Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.5518. Min Act: -0.1700
Data Index: 1075436 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.5204. Min Act: -0.1700
Data Index: 3499185 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.5204. Min Act: -0.1700
Data Index: 6202008 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.5204. Min Act: -0.1700
Data Index: 2393019 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4891. Min Act: -0.1700
Data Index: 1800066 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4891. Min Act: -0.1700
Data Index: 1409433 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4735. Min Act: -0.1700
Data Index: 4658781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4735. Min Act: -0.1700
Data Index: 6617775 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4421. Min Act: -0.1700
Data Index: 506117 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4421. Min Act: -0.1700
Data Index: 3160559 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4264. Min Act: -0.1700
Data Index: 2498653 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4108. Min Act: -0.1700
Data Index: 6687232 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4264. Min Act: -0.1700
Data Index: 8531795 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4264. Min Act: -0.1700
Data Index: 1929252 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4264. Min Act: -0.1700
Data Index: 3109604 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4108. Min Act: -0.1700
Data Index: 6505084 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4108. Min Act: -0.1700
Data Index: 467014 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4108. Min Act: -0.1700
Data Index: 3228831 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4108. Min Act: -0.1700
Data Index: 8024965 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5518. Min Range: -3.5518
Max Act: 3.4108. Min Act: -0.1700
Data Index: 6577615 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19