Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2336 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.7235. Min Act: -0.1700
Data Index: 10282 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.7062. Min Act: -0.1700
Data Index: 5685405 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.7062. Min Act: -0.1700
Data Index: 3425314 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6888. Min Act: -0.1700
Data Index: 7700613 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6715. Min Act: -0.1700
Data Index: 7898766 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6715. Min Act: -0.1700
Data Index: 8546573 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6715. Min Act: -0.1700
Data Index: 8549791 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6715. Min Act: -0.1700
Data Index: 3732026 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6715. Min Act: -0.1700
Data Index: 3722720 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6888. Min Act: -0.1700
Data Index: 1967467 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6715. Min Act: -0.1700
Data Index: 7414275 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6715. Min Act: -0.1700
Data Index: 2142137 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6367. Min Act: -0.1700
Data Index: 287956 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6367. Min Act: -0.1700
Data Index: 7437380 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6367. Min Act: -0.1699
Data Index: 3858618 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6367. Min Act: -0.1700
Data Index: 3239455 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6367. Min Act: -0.1700
Data Index: 7293241 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6367. Min Act: -0.1699
Data Index: 934320 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6541. Min Act: -0.1700
Data Index: 3101155 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7235. Min Range: -1.7235
Max Act: 1.6367. Min Act: -0.1700
Data Index: 6339790 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19