Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0307. Min Range: -7.0307
Max Act: 7.0307. Min Act: -0.1700
Data Index: 4003903 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.9370. Min Act: -0.1700
Data Index: 3790612 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.8745. Min Act: -0.1700
Data Index: 4010457 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.8120. Min Act: -0.1700
Data Index: 6485848 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.7182. Min Act: -0.1700
Data Index: 297700 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.7182. Min Act: -0.1700
Data Index: 1335049 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.7182. Min Act: -0.1700
Data Index: 6175114 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.6870. Min Act: -0.1700
Data Index: 7024862 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.6245. Min Act: -0.1700
Data Index: 3920369 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.6557. Min Act: -0.1700
Data Index: 7447368 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.5932. Min Act: -0.1700
Data Index: 3412507 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.5932. Min Act: -0.1700
Data Index: 766336 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.5932. Min Act: -0.1700
Data Index: 4898847 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.4995. Min Act: -0.1700
Data Index: 5405763 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.5307. Min Act: -0.1700
Data Index: 5255984 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.4995. Min Act: -0.1700
Data Index: 5529340 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.4995. Min Act: -0.1700
Data Index: 2887795 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.4370. Min Act: -0.1700
Data Index: 4451905 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.4370. Min Act: -0.1700
Data Index: 3059401 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0307. Min Range: -7.0307
Max Act: 6.4057. Min Act: -0.1700
Data Index: 3990948 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19