Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1115. Min Range: -6.1115
Max Act: 6.1115. Min Act: -0.1700
Data Index: 4409337 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.9865. Min Act: -0.1700
Data Index: 6803488 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1115. Min Range: -6.1115
Max Act: 6.0178. Min Act: -0.1700
Data Index: 1090028 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.8615. Min Act: -0.1700
Data Index: 234764 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.8928. Min Act: -0.1700
Data Index: 6280507 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.8928. Min Act: -0.1700
Data Index: 7116260 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7990. Min Act: -0.1700
Data Index: 7908773 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7990. Min Act: -0.1700
Data Index: 8178393 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7990. Min Act: -0.1700
Data Index: 2935407 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.8303. Min Act: -0.1700
Data Index: 1188033 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7365. Min Act: -0.1700
Data Index: 4339966 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7365. Min Act: -0.1700
Data Index: 4409335 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7678. Min Act: -0.1700
Data Index: 5666744 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7053. Min Act: -0.1700
Data Index: 8433404 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7053. Min Act: -0.1700
Data Index: 4409350 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7053. Min Act: -0.1700
Data Index: 889574 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7053. Min Act: -0.1700
Data Index: 4663942 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7365. Min Act: -0.1700
Data Index: 1514566 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7053. Min Act: -0.1700
Data Index: 8338900 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1115. Min Range: -6.1115
Max Act: 5.7053. Min Act: -0.1700
Data Index: 8577342 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19