Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4867 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.7879. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.2536. Min Act: -0.1698
Data Index: 8514186 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.2536. Min Act: -0.1699
Data Index: 2045720 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.2536. Min Act: -0.1700
Data Index: 2479362 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.2370. Min Act: -0.1700
Data Index: 93645 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.2536. Min Act: -0.1694
Data Index: 5956578 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.2370. Min Act: -0.1699
Data Index: 3733505 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.2039. Min Act: -0.1697
Data Index: 8166612 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1540. Min Act: -0.1700
Data Index: 6667513 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1707. Min Act: -0.1700
Data Index: 52265 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1373. Min Act: -0.1700
Data Index: 7410089 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1540. Min Act: -0.1690
Data Index: 8431508 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1206. Min Act: -0.1696
Data Index: 6015437 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1373. Min Act: -0.1700
Data Index: 5034913 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1039. Min Act: -0.1700
Data Index: 6687564 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1039. Min Act: -0.1700
Data Index: 8198760 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1039. Min Act: -0.1700
Data Index: 2406766 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1039. Min Act: -0.1695
Data Index: 8668424 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1206. Min Act: -0.1643
Data Index: 1417964 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7879. Min Range: -2.7879
Max Act: 2.1039. Min Act: -0.1700
Data Index: 1825000 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19