Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 956 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.4351. Min Act: -0.1700
Data Index: 6182969 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.3101. Min Act: -0.1700
Data Index: 997344 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.2788. Min Act: -0.1700
Data Index: 724267 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.2476. Min Act: -0.1700
Data Index: 7855679 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.2788. Min Act: -0.1700
Data Index: 3775078 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.2476. Min Act: -0.1700
Data Index: 4865993 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.2476. Min Act: -0.1700
Data Index: 203935 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.2163. Min Act: -0.1700
Data Index: 2518109 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.1851. Min Act: -0.1700
Data Index: 5332455 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.1851. Min Act: -0.1700
Data Index: 8521074 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.1538. Min Act: -0.1700
Data Index: 3822416 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.1226. Min Act: -0.1700
Data Index: 5259767 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.1226. Min Act: -0.1700
Data Index: 7313234 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.1226. Min Act: -0.1700
Data Index: 7120599 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.1226. Min Act: -0.1700
Data Index: 6902974 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.0913. Min Act: -0.1700
Data Index: 3750822 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.0913. Min Act: -0.1700
Data Index: 2345585 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.1226. Min Act: -0.1700
Data Index: 2345517 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.0913. Min Act: -0.1700
Data Index: 2119106 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4351. Min Range: -5.4351
Max Act: 5.0913. Min Act: -0.1700
Data Index: 1491200 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19