Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.7795. Min Range: -14.7795
Max Act: 14.7795. Min Act: -0.1700
Data Index: 5957288 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.7170. Min Act: -0.1700
Data Index: 5845593 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.6545. Min Act: -0.1700
Data Index: 3218718 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.5295. Min Act: -0.1700
Data Index: 354638 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.3420. Min Act: -0.1700
Data Index: 4741696 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.4670. Min Act: -0.1700
Data Index: 354634 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.3420. Min Act: -0.1700
Data Index: 5035793 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.3420. Min Act: -0.1700
Data Index: 7167804 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.2795. Min Act: -0.1698
Data Index: 7847699 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.2795. Min Act: -0.1700
Data Index: 3455149 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.2795. Min Act: -0.1700
Data Index: 3494301 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.2795. Min Act: -0.1700
Data Index: 4501272 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.2795. Min Act: -0.1700
Data Index: 2935824 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.2170. Min Act: -0.1700
Data Index: 7182081 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.1545. Min Act: -0.1700
Data Index: 1296276 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.1545. Min Act: -0.1700
Data Index: 4440575 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.1545. Min Act: -0.1700
Data Index: 8576254 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.0920. Min Act: -0.1700
Data Index: 968899 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.0920. Min Act: -0.1700
Data Index: 7796746 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.7795. Min Range: -14.7795
Max Act: 13.0295. Min Act: -0.1700
Data Index: 1826308 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19