Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.5971. Min Act: -0.1700
Data Index: 8378137 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.5033. Min Act: -0.1700
Data Index: 6225458 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.5346. Min Act: -0.1700
Data Index: 7017140 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.5346. Min Act: -0.1700
Data Index: 4315929 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.5033. Min Act: -0.1700
Data Index: 5017180 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.4408. Min Act: -0.1700
Data Index: 6824061 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.4408. Min Act: -0.1700
Data Index: 8236737 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.4408. Min Act: -0.1700
Data Index: 3363335 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3783. Min Act: -0.1700
Data Index: 6480403 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3470. Min Act: -0.1700
Data Index: 873744 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3783. Min Act: -0.1700
Data Index: 6834551 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3783. Min Act: -0.1700
Data Index: 2729085 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.4096. Min Act: -0.1700
Data Index: 5691892 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3783. Min Act: -0.1700
Data Index: 6368879 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3783. Min Act: -0.1700
Data Index: 4273723 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3158. Min Act: -0.1700
Data Index: 5104971 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3470. Min Act: -0.1700
Data Index: 6802883 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3783. Min Act: -0.1700
Data Index: 569484 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3158. Min Act: -0.1700
Data Index: 1525851 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5971. Min Range: -4.5971
Max Act: 4.3470. Min Act: -0.1700
Data Index: 5216858 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19