Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3906 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.5919. Min Act: -0.1700
Data Index: 3122473 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.4357. Min Act: -0.1700
Data Index: 993510 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.4044. Min Act: -0.1700
Data Index: 3383188 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.3732. Min Act: -0.1700
Data Index: 6855312 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.3107. Min Act: -0.1700
Data Index: 4926936 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.2794. Min Act: -0.1700
Data Index: 7638285 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.2794. Min Act: -0.1700
Data Index: 6138629 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.2794. Min Act: -0.1700
Data Index: 3481762 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.2482. Min Act: -0.1700
Data Index: 7558790 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.1544. Min Act: -0.1700
Data Index: 6041095 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0919. Min Act: -0.1700
Data Index: 1272812 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0294. Min Act: -0.1700
Data Index: 8595857 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0607. Min Act: -0.1700
Data Index: 7179002 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0919. Min Act: -0.1700
Data Index: 5413370 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0919. Min Act: -0.1700
Data Index: 800285 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0294. Min Act: -0.1700
Data Index: 6309503 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0607. Min Act: -0.1700
Data Index: 3851924 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0607. Min Act: -0.1700
Data Index: 5964007 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0294. Min Act: -0.1700
Data Index: 872424 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5919. Min Range: -6.5919
Max Act: 6.0607. Min Act: -0.1700
Data Index: 7047959 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19