Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.8167. Min Act: -0.1700
Data Index: 7580781 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.8792. Min Act: -0.1700
Data Index: 3697362 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.8479. Min Act: -0.1700
Data Index: 6666375 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.7854. Min Act: -0.1700
Data Index: 1862727 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.7229. Min Act: -0.1700
Data Index: 2506839 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.7229. Min Act: -0.1700
Data Index: 7563018 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.7229. Min Act: -0.1700
Data Index: 381287 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.6917. Min Act: -0.1700
Data Index: 4769482 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.6604. Min Act: -0.1700
Data Index: 4665523 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.6604. Min Act: -0.1700
Data Index: 5907486 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.6292. Min Act: -0.1700
Data Index: 5514291 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.6604. Min Act: -0.1700
Data Index: 3332407 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.6292. Min Act: -0.1700
Data Index: 8620965 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.6292. Min Act: -0.1700
Data Index: 4058920 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.6292. Min Act: -0.1700
Data Index: 8245281 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.5979. Min Act: -0.1700
Data Index: 7269114 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.5979. Min Act: -0.1700
Data Index: 2747004 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.5979. Min Act: -0.1700
Data Index: 5069040 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.5667. Min Act: -0.1700
Data Index: 2316413 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8792. Min Range: -4.8792
Max Act: 4.5667. Min Act: -0.1700
Data Index: 5860730 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19