Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4929 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3411. Min Range: -12.3411
Max Act: 12.3411. Min Act: -0.1700
Data Index: 3662174 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.6536. Min Act: -0.1700
Data Index: 4367761 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.6536. Min Act: -0.1700
Data Index: 2497785 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.5286. Min Act: -0.1700
Data Index: 6723399 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.2786. Min Act: -0.1700
Data Index: 8537483 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.2786. Min Act: -0.1700
Data Index: 6067469 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.3411. Min Act: -0.1700
Data Index: 3008436 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.2161. Min Act: -0.1700
Data Index: 7958331 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.0911. Min Act: -0.1700
Data Index: 709089 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.1536. Min Act: -0.1700
Data Index: 1227708 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3411. Min Range: -12.3411
Max Act: 11.0911. Min Act: -0.1700
Data Index: 5543190 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3411. Min Range: -12.3411
Max Act: 10.9036. Min Act: -0.1700
Data Index: 2556537 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3411. Min Range: -12.3411
Max Act: 10.8411. Min Act: -0.1700
Data Index: 6539205 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3411. Min Range: -12.3411
Max Act: 10.8411. Min Act: -0.1700
Data Index: 3611232 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3411. Min Range: -12.3411
Max Act: 10.7786. Min Act: -0.1700
Data Index: 3068815 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3411. Min Range: -12.3411
Max Act: 10.8411. Min Act: -0.1700
Data Index: 4638754 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3411. Min Range: -12.3411
Max Act: 10.6536. Min Act: -0.1700
Data Index: 5406536 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3411. Min Range: -12.3411
Max Act: 10.6536. Min Act: -0.1700
Data Index: 5254810 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3411. Min Range: -12.3411
Max Act: 10.6536. Min Act: -0.1700
Data Index: 2890695 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3411. Min Range: -12.3411
Max Act: 10.5911. Min Act: -0.1700
Data Index: 3377489 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19