Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 617 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.5108. Min Act: -0.1700
Data Index: 2821384 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.4796. Min Act: -0.1700
Data Index: 3977020 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.4483. Min Act: -0.1700
Data Index: 8374608 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.4171. Min Act: -0.1700
Data Index: 5236289 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3546. Min Act: -0.1700
Data Index: 7455848 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3858. Min Act: -0.1700
Data Index: 6380117 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3546. Min Act: -0.1700
Data Index: 8498899 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3858. Min Act: -0.1700
Data Index: 4150886 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3546. Min Act: -0.1700
Data Index: 1208683 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3546. Min Act: -0.1700
Data Index: 533041 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3233. Min Act: -0.1700
Data Index: 4404054 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3233. Min Act: -0.1700
Data Index: 1704332 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.2921. Min Act: -0.1700
Data Index: 3681603 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3233. Min Act: -0.1700
Data Index: 8455583 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3233. Min Act: -0.1700
Data Index: 1690724 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3233. Min Act: -0.1700
Data Index: 5508505 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.2921. Min Act: -0.1700
Data Index: 8293359 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.2921. Min Act: -0.1700
Data Index: 4109004 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.2921. Min Act: -0.1700
Data Index: 7581640 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.2921. Min Act: -0.1700
Data Index: 4938085 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19