Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3641 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.8141. Min Act: -0.1700
Data Index: 5592449 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.7982. Min Act: -0.1700
Data Index: 6699634 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.7823. Min Act: -0.1700
Data Index: 469834 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.7504. Min Act: -0.1700
Data Index: 5863698 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.7344. Min Act: -0.1700
Data Index: 7655571 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.7184. Min Act: -0.1700
Data Index: 3558993 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6864. Min Act: -0.1700
Data Index: 7368471 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6864. Min Act: -0.1700
Data Index: 1935207 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6543. Min Act: -0.1700
Data Index: 4780689 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6704. Min Act: -0.1700
Data Index: 5676814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6383. Min Act: -0.1700
Data Index: 8360092 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6383. Min Act: -0.1700
Data Index: 7373316 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6543. Min Act: -0.1700
Data Index: 6805011 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6222. Min Act: -0.1700
Data Index: 357484 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6543. Min Act: -0.1700
Data Index: 7009916 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6543. Min Act: -0.1700
Data Index: 8173729 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6543. Min Act: -0.1700
Data Index: 900106 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6383. Min Act: -0.1700
Data Index: 4611294 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6383. Min Act: -0.1700
Data Index: 4929228 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8141. Min Range: -2.8141
Max Act: 2.6543. Min Act: -0.1700
Data Index: 1555647 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19