Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3936. Min Range: -7.3936
Max Act: 7.3936. Min Act: -0.1700
Data Index: 2474933 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3936. Min Range: -7.3936
Max Act: 7.0186. Min Act: -0.1700
Data Index: 3159931 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.9248. Min Act: -0.1700
Data Index: 50843 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3936. Min Range: -7.3936
Max Act: 7.0186. Min Act: -0.1700
Data Index: 6196371 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.8623. Min Act: -0.1700
Data Index: 3159936 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.7998. Min Act: -0.1700
Data Index: 8745376 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.7373. Min Act: -0.1700
Data Index: 3842602 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.7373. Min Act: -0.1700
Data Index: 2910986 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.7061. Min Act: -0.1700
Data Index: 2771126 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.7061. Min Act: -0.1700
Data Index: 1776795 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.6748. Min Act: -0.1700
Data Index: 6316929 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.6436. Min Act: -0.1700
Data Index: 7435562 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.6123. Min Act: -0.1700
Data Index: 4464586 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.5811. Min Act: -0.1700
Data Index: 8793734 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.5498. Min Act: -0.1700
Data Index: 7302992 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.5498. Min Act: -0.1700
Data Index: 5945570 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.3936. Min Act: -0.1700
Data Index: 6008879 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.3311. Min Act: -0.1700
Data Index: 3735307 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.2998. Min Act: -0.1700
Data Index: 7752962 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3936. Min Range: -7.3936
Max Act: 6.3623. Min Act: -0.1700
Data Index: 4339100 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19