Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1876 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.7295. Min Act: -0.1700
Data Index: 3980076 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.6670. Min Act: -0.1700
Data Index: 8326139 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.4795. Min Act: -0.1700
Data Index: 1737823 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.4483. Min Act: -0.1700
Data Index: 4480756 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.4170. Min Act: -0.1700
Data Index: 6105686 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.3233. Min Act: -0.1700
Data Index: 7216214 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.3233. Min Act: -0.1700
Data Index: 6551696 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.2920. Min Act: -0.1700
Data Index: 2856495 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.2920. Min Act: -0.1700
Data Index: 4378148 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.2608. Min Act: -0.1700
Data Index: 4977505 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.1983. Min Act: -0.1700
Data Index: 349164 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.2295. Min Act: -0.1700
Data Index: 2358742 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.1670. Min Act: -0.1700
Data Index: 2364349 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.1983. Min Act: -0.1700
Data Index: 4896660 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.1983. Min Act: -0.1700
Data Index: 6322792 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.1358. Min Act: -0.1700
Data Index: 3570362 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.1670. Min Act: -0.1700
Data Index: 4844996 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.1670. Min Act: -0.1700
Data Index: 7853460 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.1358. Min Act: -0.1700
Data Index: 1371844 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7295. Min Range: -6.7295
Max Act: 6.1045. Min Act: -0.1700
Data Index: 6552161 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19