Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3179 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.5349. Min Act: -0.1700
Data Index: 8718900 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.5036. Min Act: -0.1700
Data Index: 1135936 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.4099. Min Act: -0.1700
Data Index: 2591039 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.3474. Min Act: -0.1700
Data Index: 5019852 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.2536. Min Act: -0.1700
Data Index: 6750855 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.2536. Min Act: -0.1700
Data Index: 3795467 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.2224. Min Act: -0.1700
Data Index: 1644174 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.2224. Min Act: -0.1700
Data Index: 6012949 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.2224. Min Act: -0.1700
Data Index: 1031703 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.1911. Min Act: -0.1700
Data Index: 6890769 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.1911. Min Act: -0.1700
Data Index: 7373781 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.1911. Min Act: -0.1700
Data Index: 4127890 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.0974. Min Act: -0.1700
Data Index: 90805 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.0661. Min Act: -0.1700
Data Index: 7439486 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.0661. Min Act: -0.1700
Data Index: 6558301 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.0349. Min Act: -0.1700
Data Index: 7948331 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.0036. Min Act: -0.1700
Data Index: 2172128 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.0036. Min Act: -0.1700
Data Index: 3626503 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.0036. Min Act: -0.1700
Data Index: 3150018 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5349. Min Range: -7.5349
Max Act: 7.0036. Min Act: -0.1700
Data Index: 1062062 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19