Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2338 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.6083. Min Act: -0.1700
Data Index: 5297353 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.2635. Min Act: -0.1700
Data Index: 3193477 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.3733. Min Act: -0.1700
Data Index: 5708571 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.2477. Min Act: -0.1700
Data Index: 1255858 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.1691. Min Act: -0.1700
Data Index: 808909 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.2320. Min Act: -0.1700
Data Index: 4079727 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.2006. Min Act: -0.1700
Data Index: 7306508 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.1376. Min Act: -0.1700
Data Index: 6637008 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.1376. Min Act: -0.1700
Data Index: 6640556 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.0115. Min Act: -0.1700
Data Index: 4378124 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.0746. Min Act: -0.1700
Data Index: 7923725 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.0746. Min Act: -0.1700
Data Index: 5385918 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.0431. Min Act: -0.1700
Data Index: 2852632 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.0746. Min Act: -0.1700
Data Index: 6905839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.0273. Min Act: -0.1700
Data Index: 8328798 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.0273. Min Act: -0.1700
Data Index: 4388653 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.0431. Min Act: -0.1700
Data Index: 3883356 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.1061. Min Act: -0.1700
Data Index: 1012005 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6083. Min Range: -3.6083
Max Act: 3.0273. Min Act: -0.1700
Data Index: 1231327 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6083. Min Range: -3.6083
Max Act: 2.9799. Min Act: -0.1700
Data Index: 7426808 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19