Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5835 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.9985. Min Act: -0.1700
Data Index: 673405 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.9673. Min Act: -0.1700
Data Index: 6265811 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.7173. Min Act: -0.1700
Data Index: 3431110 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.7173. Min Act: -0.1700
Data Index: 7436132 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.7173. Min Act: -0.1700
Data Index: 2825 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.7485. Min Act: -0.1700
Data Index: 3078160 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.6860. Min Act: -0.1700
Data Index: 2593924 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.6548. Min Act: -0.1700
Data Index: 5608978 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.6235. Min Act: -0.1700
Data Index: 5178351 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.5610. Min Act: -0.1700
Data Index: 2413725 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.5610. Min Act: -0.1700
Data Index: 3710994 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.5610. Min Act: -0.1700
Data Index: 4149821 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.5610. Min Act: -0.1700
Data Index: 5545606 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.5298. Min Act: -0.1700
Data Index: 6145405 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.5298. Min Act: -0.1700
Data Index: 8112599 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.5298. Min Act: -0.1700
Data Index: 687882 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.4985. Min Act: -0.1700
Data Index: 7146153 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.4673. Min Act: -0.1700
Data Index: 716623 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.4673. Min Act: -0.1700
Data Index: 5445833 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9985. Min Range: -6.9985
Max Act: 6.4673. Min Act: -0.1700
Data Index: 6611841 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19