Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4369 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0253. Min Range: -5.0253
Max Act: 5.0253. Min Act: -0.1700
Data Index: 6945145 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 2372772 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7441. Min Act: -0.1700
Data Index: 4560009 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7441. Min Act: -0.1700
Data Index: 5500684 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7128. Min Act: -0.1700
Data Index: 4483142 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7128. Min Act: -0.1700
Data Index: 8012221 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6816. Min Act: -0.1700
Data Index: 2609200 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7128. Min Act: -0.1700
Data Index: 6707871 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6816. Min Act: -0.1700
Data Index: 5072574 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6503. Min Act: -0.1700
Data Index: 4344968 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6503. Min Act: -0.1700
Data Index: 459502 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6503. Min Act: -0.1700
Data Index: 4094870 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6503. Min Act: -0.1700
Data Index: 2482756 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6191. Min Act: -0.1700
Data Index: 4758476 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6191. Min Act: -0.1700
Data Index: 7095196 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.5878. Min Act: -0.1700
Data Index: 3942934 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.5878. Min Act: -0.1700
Data Index: 1131700 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.5566. Min Act: -0.1700
Data Index: 8010955 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.5878. Min Act: -0.1700
Data Index: 1433086 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.5566. Min Act: -0.1700
Data Index: 514045 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19