Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1600 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.6223. Min Act: -0.1700
Data Index: 3649773 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.5911. Min Act: -0.1700
Data Index: 8652870 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.5911. Min Act: -0.1700
Data Index: 4414869 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.4036. Min Act: -0.1700
Data Index: 7869474 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.3723. Min Act: -0.1700
Data Index: 8077937 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.3098. Min Act: -0.1700
Data Index: 336093 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.3098. Min Act: -0.1700
Data Index: 5819992 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.2786. Min Act: -0.1700
Data Index: 2694942 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.2786. Min Act: -0.1700
Data Index: 1966197 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.2786. Min Act: -0.1700
Data Index: 8408673 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.2161. Min Act: -0.1700
Data Index: 7109125 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.2161. Min Act: -0.1700
Data Index: 2733734 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.2473. Min Act: -0.1700
Data Index: 1848395 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.1536. Min Act: -0.1700
Data Index: 1202499 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.1848. Min Act: -0.1700
Data Index: 1929058 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.1848. Min Act: -0.1700
Data Index: 8804758 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.1848. Min Act: -0.1700
Data Index: 8518249 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.1536. Min Act: -0.1700
Data Index: 4703989 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.1536. Min Act: -0.1700
Data Index: 2130784 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6223. Min Range: -5.6223
Max Act: 5.1536. Min Act: -0.1700
Data Index: 5835766 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19