Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8921. Min Act: -0.1700
Data Index: 6857551 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.8296. Min Act: -0.1700
Data Index: 6897735 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7358. Min Act: -0.1700
Data Index: 3005072 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.7671. Min Act: -0.1700
Data Index: 8006069 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6733. Min Act: -0.1700
Data Index: 5359800 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6733. Min Act: -0.1700
Data Index: 7996353 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6733. Min Act: -0.1700
Data Index: 4435607 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6108. Min Act: -0.1700
Data Index: 8103965 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6421. Min Act: -0.1700
Data Index: 5219622 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6733. Min Act: -0.1700
Data Index: 2922439 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6733. Min Act: -0.1700
Data Index: 8229664 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6733. Min Act: -0.1700
Data Index: 7547617 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6421. Min Act: -0.1700
Data Index: 2066433 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6421. Min Act: -0.1700
Data Index: 1430820 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6421. Min Act: -0.1700
Data Index: 2232556 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6733. Min Act: -0.1700
Data Index: 3765190 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.5796. Min Act: -0.1700
Data Index: 1896004 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.5796. Min Act: -0.1700
Data Index: 306915 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.5796. Min Act: -0.1700
Data Index: 1084988 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8921. Min Range: -4.8921
Max Act: 4.6108. Min Act: -0.1700
Data Index: 751114 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19