Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1006 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4263. Min Range: -5.4263
Max Act: 5.4263. Min Act: -0.1700
Data Index: 4831997 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4263. Min Range: -5.4263
Max Act: 5.1138. Min Act: -0.1700
Data Index: 6370470 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4263. Min Range: -5.4263
Max Act: 5.0826. Min Act: -0.1700
Data Index: 266115 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4263. Min Range: -5.4263
Max Act: 5.0513. Min Act: -0.1700
Data Index: 137383 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4263. Min Range: -5.4263
Max Act: 5.0513. Min Act: -0.1700
Data Index: 7193093 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4263. Min Range: -5.4263
Max Act: 5.0201. Min Act: -0.1700
Data Index: 3013015 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9888. Min Act: -0.1700
Data Index: 4066061 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9888. Min Act: -0.1700
Data Index: 8411222 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9888. Min Act: -0.1700
Data Index: 1827634 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9576. Min Act: -0.1700
Data Index: 5114409 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9576. Min Act: -0.1700
Data Index: 6658520 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9576. Min Act: -0.1700
Data Index: 695054 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9576. Min Act: -0.1700
Data Index: 3585719 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9576. Min Act: -0.1700
Data Index: 2123190 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9576. Min Act: -0.1700
Data Index: 5546912 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9576. Min Act: -0.1700
Data Index: 3087048 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9263. Min Act: -0.1700
Data Index: 4165374 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.8951. Min Act: -0.1700
Data Index: 2058654 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.9263. Min Act: -0.1700
Data Index: 5700547 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4263. Min Range: -5.4263
Max Act: 4.8951. Min Act: -0.1700
Data Index: 6652722 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19