Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1356 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.5784. Min Act: -0.1700
Data Index: 6122221 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.2346. Min Act: -0.1700
Data Index: 8062454 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.2346. Min Act: -0.1700
Data Index: 5620720 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.2034. Min Act: -0.1700
Data Index: 3831683 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.1721. Min Act: -0.1700
Data Index: 1076874 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.1096. Min Act: -0.1700
Data Index: 4520719 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.0784. Min Act: -0.1700
Data Index: 8062453 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.0471. Min Act: -0.1700
Data Index: 4520724 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.0471. Min Act: -0.1700
Data Index: 1694467 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.0159. Min Act: -0.1700
Data Index: 2365703 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.0159. Min Act: -0.1700
Data Index: 4053052 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.0159. Min Act: -0.1695
Data Index: 4520723 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.0159. Min Act: -0.1636
Data Index: 4520718 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.0159. Min Act: -0.1700
Data Index: 1660451 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5784. Min Range: -6.5784
Max Act: 5.9846. Min Act: -0.1700
Data Index: 451653 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5784. Min Range: -6.5784
Max Act: 6.0159. Min Act: -0.1700
Data Index: 5842423 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5784. Min Range: -6.5784
Max Act: 5.9846. Min Act: -0.1700
Data Index: 1500597 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5784. Min Range: -6.5784
Max Act: 5.9534. Min Act: -0.1700
Data Index: 4520717 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5784. Min Range: -6.5784
Max Act: 5.9534. Min Act: -0.1700
Data Index: 998515 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5784. Min Range: -6.5784
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6527565 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19