Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1553 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.9167. Min Act: -0.1700
Data Index: 6342056 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.9167. Min Act: -0.1700
Data Index: 7936044 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.7917. Min Act: -0.1700
Data Index: 4290168 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.7292. Min Act: -0.1700
Data Index: 2031646 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.7917. Min Act: -0.1700
Data Index: 5448003 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.7917. Min Act: -0.1700
Data Index: 5668611 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.7292. Min Act: -0.1700
Data Index: 4576356 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.7292. Min Act: -0.1700
Data Index: 3302242 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.7292. Min Act: -0.1700
Data Index: 7828233 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6979. Min Act: -0.1700
Data Index: 8145643 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6979. Min Act: -0.1700
Data Index: 4116497 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6979. Min Act: -0.1700
Data Index: 686591 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.7292. Min Act: -0.1700
Data Index: 1646919 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6979. Min Act: -0.1700
Data Index: 6739477 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6979. Min Act: -0.1700
Data Index: 2952858 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6667. Min Act: -0.1700
Data Index: 4377872 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6354. Min Act: -0.1700
Data Index: 4493733 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6354. Min Act: -0.1700
Data Index: 8258076 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6354. Min Act: -0.1700
Data Index: 2858191 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9167. Min Range: -7.9167
Max Act: 7.6042. Min Act: -0.1700
Data Index: 7209924 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19