Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2749. Min Range: -8.2749
Max Act: 8.2749. Min Act: -0.1700
Data Index: 7255260 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.9624. Min Act: -0.1700
Data Index: 3604831 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.9624. Min Act: -0.1700
Data Index: 3321604 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.5874. Min Act: -0.1700
Data Index: 5679687 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.4936. Min Act: -0.1700
Data Index: 2221260 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.3061. Min Act: -0.1700
Data Index: 3321603 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.2436. Min Act: -0.1700
Data Index: 4743189 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.1186. Min Act: -0.1700
Data Index: 3260719 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.1186. Min Act: -0.1700
Data Index: 4553484 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.0874. Min Act: -0.1700
Data Index: 7705159 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.0874. Min Act: -0.1700
Data Index: 5093446 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.0874. Min Act: -0.1700
Data Index: 6039657 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.0874. Min Act: -0.1700
Data Index: 1806882 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.0561. Min Act: -0.1700
Data Index: 97186 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.0561. Min Act: -0.1700
Data Index: 3142271 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2749. Min Range: -8.2749
Max Act: 7.0249. Min Act: -0.1700
Data Index: 7438597 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2749. Min Range: -8.2749
Max Act: 6.9936. Min Act: -0.1700
Data Index: 7441267 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2749. Min Range: -8.2749
Max Act: 6.9936. Min Act: -0.1700
Data Index: 4481372 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2749. Min Range: -8.2749
Max Act: 6.9936. Min Act: -0.1700
Data Index: 2657564 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2749. Min Range: -8.2749
Max Act: 6.8999. Min Act: -0.1700
Data Index: 1922558 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19