Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.7185. Min Act: -0.1700
Data Index: 4299218 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.6716. Min Act: -0.1700
Data Index: 8128738 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.6403. Min Act: -0.1700
Data Index: 1350336 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.6090. Min Act: -0.1700
Data Index: 5866903 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.6090. Min Act: -0.1700
Data Index: 4979499 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.5777. Min Act: -0.1700
Data Index: 3148337 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.5464. Min Act: -0.1700
Data Index: 8629423 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.5307. Min Act: -0.1700
Data Index: 942582 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.5307. Min Act: -0.1700
Data Index: 182652 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4524. Min Act: -0.1700
Data Index: 3495288 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4681. Min Act: -0.1700
Data Index: 4753996 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4681. Min Act: -0.1700
Data Index: 2337614 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4681. Min Act: -0.1700
Data Index: 1179361 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4524. Min Act: -0.1700
Data Index: 182656 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4524. Min Act: -0.1700
Data Index: 1391562 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4524. Min Act: -0.1700
Data Index: 3808823 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4367. Min Act: -0.1700
Data Index: 2584334 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4211. Min Act: -0.1700
Data Index: 6957392 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4054. Min Act: -0.1700
Data Index: 1097297 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7185. Min Range: -3.7185
Max Act: 3.4054. Min Act: -0.1700
Data Index: 2404519 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19