Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.8256. Min Act: -0.1700
Data Index: 3233038 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.7319. Min Act: -0.1700
Data Index: 67273 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.7006. Min Act: -0.1700
Data Index: 934801 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.6381. Min Act: -0.1700
Data Index: 7164387 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.5131. Min Act: -0.1700
Data Index: 4867149 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.4194. Min Act: -0.1700
Data Index: 4151031 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.3881. Min Act: -0.1700
Data Index: 3153672 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.3256. Min Act: -0.1700
Data Index: 1868182 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.3256. Min Act: -0.1700
Data Index: 1019869 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2944. Min Act: -0.1700
Data Index: 2009195 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2944. Min Act: -0.1700
Data Index: 2897986 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2944. Min Act: -0.1700
Data Index: 1868181 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.3256. Min Act: -0.1700
Data Index: 6989 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2944. Min Act: -0.1700
Data Index: 5748386 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2631. Min Act: -0.1700
Data Index: 8490204 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2319. Min Act: -0.1700
Data Index: 3233037 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2319. Min Act: -0.1700
Data Index: 2707240 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2319. Min Act: -0.1700
Data Index: 952872 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2319. Min Act: -0.1700
Data Index: 775131 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8256. Min Range: -7.8256
Max Act: 7.2006. Min Act: -0.1700
Data Index: 238040 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19