Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1601 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.8660. Min Act: -0.1700
Data Index: 8416297 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.6785. Min Act: -0.1700
Data Index: 82656 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.6160. Min Act: -0.1700
Data Index: 8350052 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.6785. Min Act: -0.1700
Data Index: 726365 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.5535. Min Act: -0.1700
Data Index: 5279148 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.5535. Min Act: -0.1700
Data Index: 8599577 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.5535. Min Act: -0.1700
Data Index: 238875 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.5535. Min Act: -0.1700
Data Index: 7819526 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.4910. Min Act: -0.1700
Data Index: 8620677 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.4910. Min Act: -0.1700
Data Index: 6257140 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.4910. Min Act: -0.1700
Data Index: 7729483 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.4910. Min Act: -0.1700
Data Index: 7396425 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.5535. Min Act: -0.1700
Data Index: 2399473 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.4285. Min Act: -0.1700
Data Index: 7239383 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.4285. Min Act: -0.1700
Data Index: 899135 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.3660. Min Act: -0.1700
Data Index: 4839563 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.3660. Min Act: -0.1700
Data Index: 358383 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.3035. Min Act: -0.1700
Data Index: 8013016 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.3660. Min Act: -0.1700
Data Index: 8109230 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8660. Min Range: -9.8660
Max Act: 9.3660. Min Act: -0.1700
Data Index: 8301877 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19