Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3176 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8954. Min Range: -10.8954
Max Act: 10.8954. Min Act: -0.1700
Data Index: 5896529 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8954. Min Range: -10.8954
Max Act: 10.0829. Min Act: -0.1700
Data Index: 8019737 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8954. Min Range: -10.8954
Max Act: 10.0204. Min Act: -0.1700
Data Index: 2397373 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8954. Min Range: -10.8954
Max Act: 10.0204. Min Act: -0.1700
Data Index: 751115 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.8954. Min Act: -0.1700
Data Index: 1898119 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.8329. Min Act: -0.1700
Data Index: 7003283 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.7704. Min Act: -0.1700
Data Index: 5884043 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.7704. Min Act: -0.1700
Data Index: 1827844 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.7079. Min Act: -0.1700
Data Index: 7506345 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.7079. Min Act: -0.1700
Data Index: 7051281 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.7079. Min Act: -0.1700
Data Index: 6392410 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.6454. Min Act: -0.1700
Data Index: 7397834 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.6454. Min Act: -0.1700
Data Index: 5812208 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.5829. Min Act: -0.1700
Data Index: 4914149 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.5829. Min Act: -0.1700
Data Index: 6039869 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.5204. Min Act: -0.1700
Data Index: 241190 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.5204. Min Act: -0.1700
Data Index: 3727745 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.5204. Min Act: -0.1700
Data Index: 85006 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.5204. Min Act: -0.1700
Data Index: 2384919 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8954. Min Range: -10.8954
Max Act: 9.5204. Min Act: -0.1700
Data Index: 5691069 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19