Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2537 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.9488. Min Act: -0.1700
Data Index: 1103538 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.9148. Min Act: -0.1700
Data Index: 6181933 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8807. Min Act: -0.1700
Data Index: 2719836 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8807. Min Act: -0.1700
Data Index: 7839538 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8807. Min Act: -0.1700
Data Index: 6453622 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8977. Min Act: -0.1700
Data Index: 4915002 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8721. Min Act: -0.1700
Data Index: 5290874 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8807. Min Act: -0.1700
Data Index: 5953169 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8807. Min Act: -0.1700
Data Index: 3662866 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8550. Min Act: -0.1700
Data Index: 4111106 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8636. Min Act: -0.1700
Data Index: 3983426 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8550. Min Act: -0.1700
Data Index: 1742591 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8379. Min Act: -0.1700
Data Index: 3934234 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8550. Min Act: -0.1700
Data Index: 373828 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8550. Min Act: -0.1700
Data Index: 3280245 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8550. Min Act: -0.1700
Data Index: 1177717 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8550. Min Act: -0.1700
Data Index: 3468344 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8293. Min Act: -0.1700
Data Index: 1501642 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8464. Min Act: -0.1700
Data Index: 493469 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9488. Min Range: -1.9488
Max Act: 1.8379. Min Act: -0.1700
Data Index: 4449358 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19