Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3718 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1076. Min Range: -5.1076
Max Act: 5.1076. Min Act: -0.1700
Data Index: 4511109 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1076. Min Range: -5.1076
Max Act: 5.1076. Min Act: -0.1700
Data Index: 1174129 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1076. Min Range: -5.1076
Max Act: 5.1076. Min Act: -0.1700
Data Index: 2564602 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.9826. Min Act: -0.1700
Data Index: 3734697 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.9514. Min Act: -0.1700
Data Index: 4890384 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.9826. Min Act: -0.1700
Data Index: 1867308 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.9514. Min Act: -0.1700
Data Index: 4258377 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.9201. Min Act: -0.1700
Data Index: 922091 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.9201. Min Act: -0.1700
Data Index: 3796985 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.8889. Min Act: -0.1700
Data Index: 4484993 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.8576. Min Act: -0.1700
Data Index: 6877936 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.8576. Min Act: -0.1700
Data Index: 5104296 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.8264. Min Act: -0.1700
Data Index: 4126544 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.8264. Min Act: -0.1700
Data Index: 668152 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.8264. Min Act: -0.1700
Data Index: 6188434 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.8264. Min Act: -0.1700
Data Index: 3981937 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.8264. Min Act: -0.1700
Data Index: 5684852 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.8264. Min Act: -0.1700
Data Index: 3933955 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.7951. Min Act: -0.1700
Data Index: 3367485 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1076. Min Range: -5.1076
Max Act: 4.7951. Min Act: -0.1700
Data Index: 281205 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19