Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.3684. Min Act: -0.1700
Data Index: 3357864 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.1809. Min Act: -0.1700
Data Index: 1323552 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.1809. Min Act: -0.1700
Data Index: 38232 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.1496. Min Act: -0.1700
Data Index: 3970679 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.1184. Min Act: -0.1700
Data Index: 1204254 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.1184. Min Act: -0.1700
Data Index: 4139430 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.1496. Min Act: -0.1700
Data Index: 7665650 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.1184. Min Act: -0.1700
Data Index: 5683248 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.1184. Min Act: -0.1700
Data Index: 6373136 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.1184. Min Act: -0.1700
Data Index: 4145523 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.0871. Min Act: -0.1700
Data Index: 7711338 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.0246. Min Act: -0.1700
Data Index: 7094324 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.0246. Min Act: -0.1700
Data Index: 7742323 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3684. Min Range: -6.3684
Max Act: 6.0246. Min Act: -0.1700
Data Index: 4145524 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3684. Min Range: -6.3684
Max Act: 5.9934. Min Act: -0.1700
Data Index: 829714 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3684. Min Range: -6.3684
Max Act: 5.9621. Min Act: -0.1700
Data Index: 6967999 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3684. Min Range: -6.3684
Max Act: 5.8996. Min Act: -0.1700
Data Index: 1314536 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3684. Min Range: -6.3684
Max Act: 5.9309. Min Act: -0.1700
Data Index: 790824 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3684. Min Range: -6.3684
Max Act: 5.8996. Min Act: -0.1700
Data Index: 6439179 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3684. Min Range: -6.3684
Max Act: 5.8996. Min Act: -0.1700
Data Index: 3326363 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19