Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1872 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 5564245 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 3220315 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2411. Min Act: -0.1700
Data Index: 4337714 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2254. Min Act: -0.1700
Data Index: 2329991 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2254. Min Act: -0.1700
Data Index: 7460428 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2254. Min Act: -0.1700
Data Index: 186227 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2254. Min Act: -0.1700
Data Index: 8189885 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2254. Min Act: -0.1700
Data Index: 1758401 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2097. Min Act: -0.1700
Data Index: 7866304 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2097. Min Act: -0.1700
Data Index: 2096267 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2097. Min Act: -0.1700
Data Index: 7402324 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2097. Min Act: -0.1700
Data Index: 305334 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2097. Min Act: -0.1700
Data Index: 1511897 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2097. Min Act: -0.1700
Data Index: 3773484 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.1940. Min Act: -0.1700
Data Index: 1944972 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.1940. Min Act: -0.1700
Data Index: 6412158 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.1782. Min Act: -0.1700
Data Index: 7309697 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.1940. Min Act: -0.1700
Data Index: 6386182 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.1940. Min Act: -0.1700
Data Index: 293672 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.1782. Min Act: -0.1700
Data Index: 612889 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19