Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1359 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1669. Min Range: -8.1669
Max Act: 8.1669. Min Act: -0.1700
Data Index: 4189703 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1669. Min Range: -8.1669
Max Act: 8.0419. Min Act: -0.1700
Data Index: 8438808 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.7919. Min Act: -0.1700
Data Index: 8438796 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.7294. Min Act: -0.1700
Data Index: 1119211 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.7294. Min Act: -0.1700
Data Index: 4322947 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.5419. Min Act: -0.1700
Data Index: 477250 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.4794. Min Act: -0.1700
Data Index: 2887441 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.4169. Min Act: -0.1700
Data Index: 6459272 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.3857. Min Act: -0.1700
Data Index: 8438797 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.4169. Min Act: -0.1700
Data Index: 5039663 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.2919. Min Act: -0.1700
Data Index: 5124886 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.2919. Min Act: -0.1700
Data Index: 4965962 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.1669. Min Act: -0.1700
Data Index: 8237080 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.1669. Min Act: -0.1700
Data Index: 2388175 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.1982. Min Act: -0.1700
Data Index: 2223740 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.1982. Min Act: -0.1700
Data Index: 6683861 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.1044. Min Act: -0.1700
Data Index: 5424143 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.0732. Min Act: -0.1700
Data Index: 2745089 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.1357. Min Act: -0.1700
Data Index: 106413 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1669. Min Range: -8.1669
Max Act: 7.1669. Min Act: -0.1700
Data Index: 8339796 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19