Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3786 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0177. Min Range: -7.0177
Max Act: 7.0177. Min Act: -0.1700
Data Index: 3703142 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0177. Min Range: -7.0177
Max Act: 7.0177. Min Act: -0.1700
Data Index: 2571079 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.8302. Min Act: -0.1700
Data Index: 1423994 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.8302. Min Act: -0.1700
Data Index: 6307218 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.7677. Min Act: -0.1700
Data Index: 5263925 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.7365. Min Act: -0.1700
Data Index: 187557 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.7052. Min Act: -0.1700
Data Index: 3141978 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.7052. Min Act: -0.1700
Data Index: 1119113 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6740. Min Act: -0.1700
Data Index: 20437 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6740. Min Act: -0.1700
Data Index: 4709178 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6740. Min Act: -0.1700
Data Index: 2121356 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6427. Min Act: -0.1700
Data Index: 6931696 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6427. Min Act: -0.1700
Data Index: 3036019 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6427. Min Act: -0.1700
Data Index: 5377674 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6115. Min Act: -0.1700
Data Index: 6542774 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6115. Min Act: -0.1700
Data Index: 7210639 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6115. Min Act: -0.1700
Data Index: 4169575 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6115. Min Act: -0.1700
Data Index: 4706871 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.5802. Min Act: -0.1700
Data Index: 3305185 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0177. Min Range: -7.0177
Max Act: 6.6115. Min Act: -0.1700
Data Index: 3580854 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19