Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2466 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1336. Min Range: -5.1336
Max Act: 5.1336. Min Act: -0.1700
Data Index: 1323247 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1336. Min Range: -5.1336
Max Act: 5.1024. Min Act: -0.1700
Data Index: 8581372 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1336. Min Range: -5.1336
Max Act: 5.0399. Min Act: -0.1700
Data Index: 1207377 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1336. Min Range: -5.1336
Max Act: 5.0086. Min Act: -0.1700
Data Index: 8553944 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9461. Min Act: -0.1700
Data Index: 3129062 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9774. Min Act: -0.1700
Data Index: 6832739 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9461. Min Act: -0.1700
Data Index: 8689067 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9461. Min Act: -0.1700
Data Index: 3964113 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9149. Min Act: -0.1700
Data Index: 3622264 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9149. Min Act: -0.1700
Data Index: 6026 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9149. Min Act: -0.1700
Data Index: 4512886 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9149. Min Act: -0.1700
Data Index: 6388136 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9149. Min Act: -0.1700
Data Index: 1022209 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.8836. Min Act: -0.1700
Data Index: 3564630 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.9149. Min Act: -0.1700
Data Index: 5150053 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.8836. Min Act: -0.1700
Data Index: 7806391 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.8211. Min Act: -0.1700
Data Index: 7354131 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.7899. Min Act: -0.1700
Data Index: 2277184 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.7586. Min Act: -0.1700
Data Index: 3147836 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1336. Min Range: -5.1336
Max Act: 4.8211. Min Act: -0.1700
Data Index: 3625871 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19