Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4152 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.7485. Min Act: -0.1700
Data Index: 1274572 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.7173. Min Act: -0.1700
Data Index: 4656375 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.6860. Min Act: -0.1700
Data Index: 2783183 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.6860. Min Act: -0.1700
Data Index: 1741694 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5610. Min Act: -0.1700
Data Index: 6035816 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5610. Min Act: -0.1700
Data Index: 7606692 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5610. Min Act: -0.1700
Data Index: 3396317 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5923. Min Act: -0.1700
Data Index: 8641144 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5298. Min Act: -0.1700
Data Index: 2712180 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5298. Min Act: -0.1700
Data Index: 3804476 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5298. Min Act: -0.1700
Data Index: 8278328 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5298. Min Act: -0.1700
Data Index: 8344459 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.4985. Min Act: -0.1700
Data Index: 4929776 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.4985. Min Act: -0.1700
Data Index: 2681687 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.4985. Min Act: -0.1700
Data Index: 348570 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.4985. Min Act: -0.1700
Data Index: 8301431 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.4985. Min Act: -0.1700
Data Index: 948103 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.4985. Min Act: -0.1700
Data Index: 4118646 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.4985. Min Act: -0.1700
Data Index: 1379494 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.4673. Min Act: -0.1700
Data Index: 5627853 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19