Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2727. Min Range: -8.2727
Max Act: 8.2727. Min Act: -0.1700
Data Index: 4950054 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2727. Min Range: -8.2727
Max Act: 8.2727. Min Act: -0.1700
Data Index: 6074550 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2727. Min Range: -8.2727
Max Act: 8.2102. Min Act: -0.1700
Data Index: 7955301 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2727. Min Range: -8.2727
Max Act: 8.1477. Min Act: -0.1700
Data Index: 7686189 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2727. Min Range: -8.2727
Max Act: 8.1477. Min Act: -0.1700
Data Index: 2316653 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2727. Min Range: -8.2727
Max Act: 8.2102. Min Act: -0.1700
Data Index: 6091025 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2727. Min Range: -8.2727
Max Act: 8.0852. Min Act: -0.1700
Data Index: 6159058 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2727. Min Range: -8.2727
Max Act: 8.0227. Min Act: -0.1700
Data Index: 1609948 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2727. Min Range: -8.2727
Max Act: 8.0227. Min Act: -0.1700
Data Index: 5573335 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.9602. Min Act: -0.1700
Data Index: 7820648 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.9602. Min Act: -0.1700
Data Index: 8805928 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.8977. Min Act: -0.1700
Data Index: 1956098 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.8977. Min Act: -0.1700
Data Index: 3905903 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.9602. Min Act: -0.1700
Data Index: 1430863 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.8977. Min Act: -0.1700
Data Index: 4622093 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.8977. Min Act: -0.1700
Data Index: 5899688 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.8977. Min Act: -0.1700
Data Index: 1413360 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.8352. Min Act: -0.1700
Data Index: 2516383 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.8352. Min Act: -0.1700
Data Index: 1563250 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2727. Min Range: -8.2727
Max Act: 7.8977. Min Act: -0.1700
Data Index: 6516767 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19