Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2068. Min Range: -6.2068
Max Act: 6.2068. Min Act: -0.1700
Data Index: 1840628 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2068. Min Range: -6.2068
Max Act: 6.0818. Min Act: -0.1700
Data Index: 3983353 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2068. Min Range: -6.2068
Max Act: 6.0818. Min Act: -0.1700
Data Index: 1057685 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2068. Min Range: -6.2068
Max Act: 6.0818. Min Act: -0.1700
Data Index: 4991142 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2068. Min Range: -6.2068
Max Act: 6.0506. Min Act: -0.1700
Data Index: 1709445 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2068. Min Range: -6.2068
Max Act: 6.0506. Min Act: -0.1700
Data Index: 955702 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9881. Min Act: -0.1700
Data Index: 145446 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9568. Min Act: -0.1700
Data Index: 1226923 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9881. Min Act: -0.1700
Data Index: 3510326 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9568. Min Act: -0.1700
Data Index: 7925133 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9256. Min Act: -0.1700
Data Index: 2476616 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9568. Min Act: -0.1700
Data Index: 5739860 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9568. Min Act: -0.1700
Data Index: 324049 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9881. Min Act: -0.1700
Data Index: 955699 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9256. Min Act: -0.1700
Data Index: 6316396 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9256. Min Act: -0.1700
Data Index: 5527764 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9256. Min Act: -0.1700
Data Index: 5330848 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9256. Min Act: -0.1700
Data Index: 3085680 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.9256. Min Act: -0.1700
Data Index: 462630 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2068. Min Range: -6.2068
Max Act: 5.8943. Min Act: -0.1700
Data Index: 7084911 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19