Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.8885. Min Act: -0.1700
Data Index: 8613138 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7010. Min Act: -0.1700
Data Index: 1957656 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.6698. Min Act: -0.1700
Data Index: 6193881 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.5448. Min Act: -0.1700
Data Index: 2978171 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.3260. Min Act: -0.1700
Data Index: 8410524 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.2948. Min Act: -0.1700
Data Index: 3503861 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.3260. Min Act: -0.1700
Data Index: 1973818 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.2323. Min Act: -0.1700
Data Index: 5075728 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.2635. Min Act: -0.1700
Data Index: 5250163 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.2635. Min Act: -0.1700
Data Index: 2627451 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.2010. Min Act: -0.1700
Data Index: 7350152 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.1385. Min Act: -0.1700
Data Index: 3410154 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.1698. Min Act: -0.1700
Data Index: 577340 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.1698. Min Act: -0.1700
Data Index: 928585 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.1698. Min Act: -0.1700
Data Index: 1420735 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.1073. Min Act: -0.1700
Data Index: 2181104 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.1698. Min Act: -0.1700
Data Index: 960566 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.1073. Min Act: -0.1700
Data Index: 488865 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.1385. Min Act: -0.1700
Data Index: 8499575 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.1698. Min Act: -0.1700
Data Index: 6246643 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19