Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1851 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.7138. Min Act: -0.1700
Data Index: 8132141 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.5887. Min Act: -0.1700
Data Index: 3888891 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.4950. Min Act: -0.1700
Data Index: 7407681 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.4637. Min Act: -0.1700
Data Index: 33524 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.3075. Min Act: -0.1700
Data Index: 3259721 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.3387. Min Act: -0.1700
Data Index: 803403 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.2762. Min Act: -0.1700
Data Index: 2018780 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.2450. Min Act: -0.1700
Data Index: 3860107 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.2762. Min Act: -0.1700
Data Index: 2377586 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.1825. Min Act: -0.1700
Data Index: 6355003 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.1200. Min Act: -0.1700
Data Index: 7877300 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.1825. Min Act: -0.1700
Data Index: 8286149 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.1200. Min Act: -0.1700
Data Index: 2862637 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.1200. Min Act: -0.1700
Data Index: 8366463 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.0574. Min Act: -0.1700
Data Index: 4603039 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.0574. Min Act: -0.1700
Data Index: 7519904 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.0262. Min Act: -0.1700
Data Index: 6119901 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.0574. Min Act: -0.1700
Data Index: 7761358 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.0106. Min Act: -0.1700
Data Index: 5291206 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7138. Min Range: -4.7138
Max Act: 4.0262. Min Act: -0.1700
Data Index: 882089 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19