Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2868 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.5076. Min Act: -0.1700
Data Index: 6717822 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.3826. Min Act: -0.1700
Data Index: 539166 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.3826. Min Act: -0.1700
Data Index: 6717823 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.3201. Min Act: -0.1700
Data Index: 2044346 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.2576. Min Act: -0.1700
Data Index: 13794 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.2889. Min Act: -0.1700
Data Index: 5222538 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.2576. Min Act: -0.1700
Data Index: 3212583 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.2576. Min Act: -0.1700
Data Index: 5891064 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.2576. Min Act: -0.1700
Data Index: 4515647 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.2264. Min Act: -0.1700
Data Index: 7187840 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.2264. Min Act: -0.1700
Data Index: 7261011 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.2264. Min Act: -0.1700
Data Index: 6156538 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.2264. Min Act: -0.1700
Data Index: 8015509 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.1951. Min Act: -0.1700
Data Index: 5765124 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.1951. Min Act: -0.1700
Data Index: 3944327 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.1951. Min Act: -0.1700
Data Index: 3089320 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.1951. Min Act: -0.1700
Data Index: 684385 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.1951. Min Act: -0.1700
Data Index: 3175325 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.1639. Min Act: -0.1700
Data Index: 822188 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5076. Min Range: -4.5076
Max Act: 4.1951. Min Act: -0.1700
Data Index: 845908 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19