Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1130 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0334. Min Range: -5.0334
Max Act: 5.0334. Min Act: -0.1700
Data Index: 4584791 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.9709. Min Act: -0.1700
Data Index: 425213 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.9397. Min Act: -0.1700
Data Index: 4662757 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.8772. Min Act: -0.1700
Data Index: 8746175 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.8147. Min Act: -0.1700
Data Index: 687973 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.7522. Min Act: -0.1700
Data Index: 7601635 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.7522. Min Act: -0.1700
Data Index: 1569816 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.6897. Min Act: -0.1700
Data Index: 1348198 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.5959. Min Act: -0.1700
Data Index: 6182541 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.6272. Min Act: -0.1700
Data Index: 367508 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.5959. Min Act: -0.1700
Data Index: 5931459 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.5959. Min Act: -0.1700
Data Index: 5535916 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.6272. Min Act: -0.1700
Data Index: 1027745 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.5959. Min Act: -0.1700
Data Index: 7334820 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.5647. Min Act: -0.1700
Data Index: 3617891 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.5334. Min Act: -0.1700
Data Index: 1899983 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.5334. Min Act: -0.1700
Data Index: 4325004 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.5022. Min Act: -0.1700
Data Index: 5932858 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.5022. Min Act: -0.1700
Data Index: 3951597 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0334. Min Range: -5.0334
Max Act: 4.4709. Min Act: -0.1700
Data Index: 8348500 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19