Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2560 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.4265. Min Act: -0.1700
Data Index: 8018256 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.3952. Min Act: -0.1700
Data Index: 14386 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2696. Min Act: -0.1700
Data Index: 3686855 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2225. Min Act: -0.1700
Data Index: 1022722 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.1910. Min Act: -0.1700
Data Index: 4143380 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.1910. Min Act: -0.1700
Data Index: 1730787 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.1438. Min Act: -0.1700
Data Index: 3870683 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.1123. Min Act: -0.1700
Data Index: 3691430 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.1281. Min Act: -0.1700
Data Index: 2047468 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.1123. Min Act: -0.1700
Data Index: 6199831 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.1281. Min Act: -0.1700
Data Index: 6193251 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.1123. Min Act: -0.1700
Data Index: 6745236 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.0966. Min Act: -0.1700
Data Index: 4802218 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.1123. Min Act: -0.1700
Data Index: 4102641 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.0966. Min Act: -0.1700
Data Index: 5164175 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.0808. Min Act: -0.1700
Data Index: 4773882 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.0808. Min Act: -0.1700
Data Index: 6367545 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.0966. Min Act: -0.1700
Data Index: 4642182 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.0650. Min Act: -0.1700
Data Index: 7324372 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.0650. Min Act: -0.1700
Data Index: 1491739 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19