Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 485 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.9854. Min Act: -0.1700
Data Index: 399793 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.7354. Min Act: -0.1700
Data Index: 507138 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.5479. Min Act: -0.1700
Data Index: 6464367 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.5479. Min Act: -0.1700
Data Index: 4451795 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.4854. Min Act: -0.1700
Data Index: 8771604 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.4229. Min Act: -0.1700
Data Index: 6477819 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.4229. Min Act: -0.1700
Data Index: 5641231 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.3604. Min Act: -0.1700
Data Index: 5754856 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.2979. Min Act: -0.1700
Data Index: 8168365 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.2979. Min Act: -0.1700
Data Index: 3416783 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.2979. Min Act: -0.1700
Data Index: 2397615 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.2979. Min Act: -0.1700
Data Index: 8551072 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.2979. Min Act: -0.1700
Data Index: 3933610 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.2354. Min Act: -0.1700
Data Index: 2998361 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.2354. Min Act: -0.1700
Data Index: 5282078 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.2354. Min Act: -0.1700
Data Index: 6464373 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.1729. Min Act: -0.1700
Data Index: 3378095 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.1729. Min Act: -0.1700
Data Index: 7594988 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.1729. Min Act: -0.1700
Data Index: 6599314 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9854. Min Range: -8.9854
Max Act: 8.1729. Min Act: -0.1700
Data Index: 4156309 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19