Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.4203. Min Act: -0.1700
Data Index: 780329 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.3549. Min Act: -0.1700
Data Index: 3563786 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.3549. Min Act: -0.1692
Data Index: 5275439 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.3549. Min Act: -0.1700
Data Index: 6513927 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.3549. Min Act: -0.1700
Data Index: 1342987 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.3221. Min Act: -0.1700
Data Index: 471305 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.3385. Min Act: -0.1700
Data Index: 279394 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.3057. Min Act: -0.1700
Data Index: 1027194 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.3057. Min Act: -0.1700
Data Index: 1913784 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2892. Min Act: -0.1700
Data Index: 7831378 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2728. Min Act: -0.1700
Data Index: 8646108 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2563. Min Act: -0.1700
Data Index: 232294 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2397. Min Act: -0.1700
Data Index: 7542166 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2397. Min Act: -0.1700
Data Index: 1789739 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2563. Min Act: -0.1700
Data Index: 7777550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2232. Min Act: -0.1700
Data Index: 4324504 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2232. Min Act: -0.1700
Data Index: 8408377 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.1900. Min Act: -0.1700
Data Index: 6629878 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2232. Min Act: -0.1700
Data Index: 2340321 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4203. Min Range: -2.4203
Max Act: 2.2066. Min Act: -0.1700
Data Index: 3391772 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19