Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4887 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.5147. Min Act: -0.1700
Data Index: 7108445 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.4522. Min Act: -0.1700
Data Index: 6534036 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.4210. Min Act: -0.1700
Data Index: 7410007 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.3585. Min Act: -0.1700
Data Index: 4632937 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.2960. Min Act: -0.1700
Data Index: 5143274 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.2335. Min Act: -0.1700
Data Index: 5926087 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.1397. Min Act: -0.1700
Data Index: 5744781 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.1397. Min Act: -0.1700
Data Index: 1001055 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.1085. Min Act: -0.1700
Data Index: 2126251 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.1085. Min Act: -0.1700
Data Index: 5111142 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.1085. Min Act: -0.1700
Data Index: 2143457 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.0772. Min Act: -0.1700
Data Index: 16826 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.0460. Min Act: -0.1700
Data Index: 7540935 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.0147. Min Act: -0.1700
Data Index: 5534774 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.0147. Min Act: -0.1700
Data Index: 2999073 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5147. Min Range: -6.5147
Max Act: 6.0147. Min Act: -0.1700
Data Index: 1369914 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5147. Min Range: -6.5147
Max Act: 5.9835. Min Act: -0.1700
Data Index: 6214769 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5147. Min Range: -6.5147
Max Act: 5.9835. Min Act: -0.1700
Data Index: 4237046 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5147. Min Range: -6.5147
Max Act: 5.9835. Min Act: -0.1700
Data Index: 1315751 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5147. Min Range: -6.5147
Max Act: 5.9835. Min Act: -0.1700
Data Index: 2673605 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19