Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4605 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.3226. Min Act: -0.1700
Data Index: 2503686 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.2127. Min Act: -0.1700
Data Index: 1098325 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.1969. Min Act: -0.1700
Data Index: 8725633 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.1497. Min Act: -0.1700
Data Index: 4099199 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.1340. Min Act: -0.1700
Data Index: 1851150 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.1497. Min Act: -0.1700
Data Index: 325077 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.1182. Min Act: -0.1700
Data Index: 8408305 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.1025. Min Act: -0.1700
Data Index: 4715640 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.1025. Min Act: -0.1700
Data Index: 4373861 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0867. Min Act: -0.1700
Data Index: 3523823 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0709. Min Act: -0.1700
Data Index: 6991142 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0709. Min Act: -0.1700
Data Index: 8751664 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0867. Min Act: -0.1700
Data Index: 1821730 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0552. Min Act: -0.1700
Data Index: 3243614 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0709. Min Act: -0.1700
Data Index: 3523822 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0552. Min Act: -0.1700
Data Index: 6635858 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0552. Min Act: -0.1700
Data Index: 788048 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0552. Min Act: -0.1700
Data Index: 1730737 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0236. Min Act: -0.1700
Data Index: 5072540 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3226. Min Range: -3.3226
Max Act: 3.0236. Min Act: -0.1700
Data Index: 2113806 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19