Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4228 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1876. Min Range: -7.1876
Max Act: 7.1876. Min Act: -0.1700
Data Index: 1887802 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1876. Min Range: -7.1876
Max Act: 7.1251. Min Act: -0.1700
Data Index: 869163 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.9376. Min Act: -0.1700
Data Index: 1547635 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.9064. Min Act: -0.1700
Data Index: 6933991 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.9376. Min Act: -0.1700
Data Index: 6242398 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.8439. Min Act: -0.1700
Data Index: 8586865 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.8751. Min Act: -0.1700
Data Index: 2868325 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.8439. Min Act: -0.1700
Data Index: 5396804 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.8751. Min Act: -0.1700
Data Index: 5389732 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.8439. Min Act: -0.1700
Data Index: 3184122 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.8126. Min Act: -0.1700
Data Index: 488079 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.8126. Min Act: -0.1700
Data Index: 869357 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7814. Min Act: -0.1700
Data Index: 422870 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7814. Min Act: -0.1700
Data Index: 7323134 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7814. Min Act: -0.1700
Data Index: 4829726 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7501. Min Act: -0.1700
Data Index: 2113348 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7501. Min Act: -0.1700
Data Index: 3332904 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7189. Min Act: -0.1700
Data Index: 4916340 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7189. Min Act: -0.1700
Data Index: 4514251 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.6876. Min Act: -0.1700
Data Index: 1489514 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19