Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.7357. Min Act: -0.1700
Data Index: 8811228 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.6107. Min Act: -0.1700
Data Index: 5951104 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.5795. Min Act: -0.1700
Data Index: 6767825 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.5795. Min Act: -0.1700
Data Index: 3446553 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.5795. Min Act: -0.1700
Data Index: 421113 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.5482. Min Act: -0.1700
Data Index: 6938736 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.5482. Min Act: -0.1700
Data Index: 5015387 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.5170. Min Act: -0.1700
Data Index: 5071172 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.5170. Min Act: -0.1700
Data Index: 3697565 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.4857. Min Act: -0.1700
Data Index: 2162233 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.4857. Min Act: -0.1700
Data Index: 8004039 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.5170. Min Act: -0.1700
Data Index: 1305011 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.5170. Min Act: -0.1700
Data Index: 2410780 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.4857. Min Act: -0.1700
Data Index: 3565187 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.4545. Min Act: -0.1700
Data Index: 2525 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.4545. Min Act: -0.1700
Data Index: 2956916 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.4857. Min Act: -0.1700
Data Index: 6669101 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.4545. Min Act: -0.1700
Data Index: 6759842 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.4232. Min Act: -0.1700
Data Index: 3597349 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7357. Min Range: -4.7357
Max Act: 4.4232. Min Act: -0.1700
Data Index: 5467279 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19