Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2685 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.9911. Min Act: -0.1700
Data Index: 7401085 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.7411. Min Act: -0.1700
Data Index: 6653219 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.6786. Min Act: -0.1700
Data Index: 7066335 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.7098. Min Act: -0.1700
Data Index: 7684939 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.7098. Min Act: -0.1700
Data Index: 2949680 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.7098. Min Act: -0.1700
Data Index: 2957165 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.6161. Min Act: -0.1700
Data Index: 5670139 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5848. Min Act: -0.1700
Data Index: 7346848 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5848. Min Act: -0.1700
Data Index: 8307087 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5536. Min Act: -0.1700
Data Index: 6448691 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.4911. Min Act: -0.1700
Data Index: 6271794 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.4598. Min Act: -0.1700
Data Index: 5817011 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.4911. Min Act: -0.1700
Data Index: 4094792 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.4286. Min Act: -0.1700
Data Index: 4289226 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.5223. Min Act: -0.1700
Data Index: 6665773 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.4286. Min Act: -0.1700
Data Index: 8395592 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.4286. Min Act: -0.1700
Data Index: 6950185 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.3348. Min Act: -0.1700
Data Index: 5180698 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.4286. Min Act: -0.1700
Data Index: 7342965 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9911. Min Range: -5.9911
Max Act: 5.3973. Min Act: -0.1700
Data Index: 2793633 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19