Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.9007. Min Act: -0.1700
Data Index: 1827992 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.8069. Min Act: -0.1700
Data Index: 6816230 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.7757. Min Act: -0.1700
Data Index: 1776080 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.6819. Min Act: -0.1700
Data Index: 8397964 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.6194. Min Act: -0.1700
Data Index: 6125206 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.6507. Min Act: -0.1700
Data Index: 8436042 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.6507. Min Act: -0.1700
Data Index: 1537291 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5882. Min Act: -0.1700
Data Index: 8369362 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.6194. Min Act: -0.1700
Data Index: 6771382 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.6194. Min Act: -0.1700
Data Index: 5848409 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5882. Min Act: -0.1700
Data Index: 3720341 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5882. Min Act: -0.1700
Data Index: 7957681 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5882. Min Act: -0.1700
Data Index: 1397330 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.6194. Min Act: -0.1700
Data Index: 3612906 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5882. Min Act: -0.1700
Data Index: 6830718 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5882. Min Act: -0.1700
Data Index: 96348 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5882. Min Act: -0.1700
Data Index: 1387302 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5569. Min Act: -0.1700
Data Index: 7768285 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5569. Min Act: -0.1700
Data Index: 203893 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9007. Min Range: -4.9007
Max Act: 4.5569. Min Act: -0.1700
Data Index: 1045507 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19