Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.3703. Min Act: -0.1700
Data Index: 5782341 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.3539. Min Act: -0.1700
Data Index: 5491955 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.3211. Min Act: -0.1700
Data Index: 1866539 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.3211. Min Act: -0.1700
Data Index: 7566327 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.3047. Min Act: -0.1699
Data Index: 7839679 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.2552. Min Act: -0.1700
Data Index: 5377667 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.2552. Min Act: -0.1700
Data Index: 8430305 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.2221. Min Act: -0.1700
Data Index: 1656784 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.2056. Min Act: -0.1700
Data Index: 5792751 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.2221. Min Act: -0.1700
Data Index: 6373420 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.2056. Min Act: -0.1700
Data Index: 5537746 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.2221. Min Act: -0.1700
Data Index: 8073994 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.1890. Min Act: -0.1700
Data Index: 895397 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.1890. Min Act: -0.1700
Data Index: 7361280 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.1723. Min Act: -0.1700
Data Index: 3468697 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.1890. Min Act: -0.1700
Data Index: 7091280 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.1890. Min Act: -0.1700
Data Index: 6167395 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.1890. Min Act: -0.1699
Data Index: 2301976 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.1890. Min Act: -0.1700
Data Index: 4972706 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3703. Min Range: -2.3703
Max Act: 2.1723. Min Act: -0.1700
Data Index: 6596443 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19