Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1861 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.5280. Min Act: -0.1700
Data Index: 4807780 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.4655. Min Act: -0.1700
Data Index: 8634236 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.3405. Min Act: -0.1700
Data Index: 8039664 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.3405. Min Act: -0.1700
Data Index: 2556946 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.2155. Min Act: -0.1700
Data Index: 6825909 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.2780. Min Act: -0.1700
Data Index: 7567986 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.2155. Min Act: -0.1700
Data Index: 6020763 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.2780. Min Act: -0.1700
Data Index: 587501 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.1530. Min Act: -0.1700
Data Index: 2958989 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.1530. Min Act: -0.1700
Data Index: 5377055 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.1530. Min Act: -0.1700
Data Index: 4494336 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.1530. Min Act: -0.1700
Data Index: 2822542 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.0905. Min Act: -0.1700
Data Index: 2473501 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.2155. Min Act: -0.1700
Data Index: 3974416 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.0905. Min Act: -0.1700
Data Index: 6076113 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.1530. Min Act: -0.1700
Data Index: 1132703 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.0905. Min Act: -0.1700
Data Index: 1085627 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.0905. Min Act: -0.1700
Data Index: 292801 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.0905. Min Act: -0.1700
Data Index: 2874345 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5280. Min Range: -9.5280
Max Act: 9.0905. Min Act: -0.1700
Data Index: 1275589 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19