Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1970 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.9586. Min Act: -0.1700
Data Index: 3034914 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.4586. Min Act: -0.1700
Data Index: 8343399 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.3648. Min Act: -0.1700
Data Index: 4682402 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.3961. Min Act: -0.1700
Data Index: 1921717 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.3336. Min Act: -0.1700
Data Index: 833620 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.3336. Min Act: -0.1700
Data Index: 5486648 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.3023. Min Act: -0.1700
Data Index: 6589210 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.3023. Min Act: -0.1700
Data Index: 5691896 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.3023. Min Act: -0.1700
Data Index: 1466601 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.1773. Min Act: -0.1700
Data Index: 7524792 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.1773. Min Act: -0.1700
Data Index: 8724363 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.2086. Min Act: -0.1700
Data Index: 7786759 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.1461. Min Act: -0.1700
Data Index: 2278419 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.2086. Min Act: -0.1700
Data Index: 7743012 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.1148. Min Act: -0.1700
Data Index: 5957393 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.1148. Min Act: -0.1700
Data Index: 7541790 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.0836. Min Act: -0.1700
Data Index: 3849150 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.1148. Min Act: -0.1700
Data Index: 8343398 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9586. Min Range: -5.9586
Max Act: 5.0836. Min Act: -0.1700
Data Index: 7970503 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9586. Min Range: -5.9586
Max Act: 4.9898. Min Act: -0.1700
Data Index: 2313439 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19