Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.4871. Min Act: -0.1700
Data Index: 7331105 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.4244. Min Act: -0.1700
Data Index: 374362 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.2675. Min Act: -0.1700
Data Index: 8448263 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.2675. Min Act: -0.1700
Data Index: 6631811 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.2204. Min Act: -0.1700
Data Index: 4375086 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.2204. Min Act: -0.1700
Data Index: 6787839 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.2204. Min Act: -0.1700
Data Index: 547014 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1732. Min Act: -0.1700
Data Index: 7908463 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1575. Min Act: -0.1700
Data Index: 7576954 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1260. Min Act: -0.1700
Data Index: 6697122 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1102. Min Act: -0.1700
Data Index: 3094496 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1417. Min Act: -0.1700
Data Index: 2383620 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1102. Min Act: -0.1700
Data Index: 7117498 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1102. Min Act: -0.1700
Data Index: 542620 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1260. Min Act: -0.1700
Data Index: 7173030 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1102. Min Act: -0.1700
Data Index: 8569800 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.1102. Min Act: -0.1700
Data Index: 1976483 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.0945. Min Act: -0.1700
Data Index: 1161299 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.0787. Min Act: -0.1700
Data Index: 5799598 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4871. Min Range: -3.4871
Max Act: 3.0945. Min Act: -0.1700
Data Index: 5015458 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19