Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6372 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7205. Min Range: -8.7205
Max Act: 8.7205. Min Act: -0.1700
Data Index: 7554511 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7205. Min Range: -8.7205
Max Act: 8.2830. Min Act: -0.1700
Data Index: 361598 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7205. Min Range: -8.7205
Max Act: 8.0955. Min Act: -0.1700
Data Index: 3771974 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.7205. Min Act: -0.1700
Data Index: 8062117 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.6580. Min Act: -0.1700
Data Index: 3907257 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.5642. Min Act: -0.1700
Data Index: 8161434 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.4080. Min Act: -0.1700
Data Index: 8716515 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.4080. Min Act: -0.1700
Data Index: 6902091 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.4080. Min Act: -0.1700
Data Index: 4130343 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.3455. Min Act: -0.1700
Data Index: 1941725 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.3455. Min Act: -0.1700
Data Index: 1069383 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.2517. Min Act: -0.1700
Data Index: 1532253 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.2517. Min Act: -0.1700
Data Index: 7158821 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.2517. Min Act: -0.1700
Data Index: 829041 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.1892. Min Act: -0.1700
Data Index: 3456399 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.1580. Min Act: -0.1700
Data Index: 2367758 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.1580. Min Act: -0.1700
Data Index: 1974533 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.1267. Min Act: -0.1700
Data Index: 1468597 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.1267. Min Act: -0.1700
Data Index: 4056362 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7205. Min Range: -8.7205
Max Act: 7.1267. Min Act: -0.1700
Data Index: 2391191 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19