Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 913 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8848. Min Act: -0.1700
Data Index: 3575717 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8689. Min Act: -0.1700
Data Index: 3397378 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8212. Min Act: -0.1700
Data Index: 5409549 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8530. Min Act: -0.1700
Data Index: 869176 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8053. Min Act: -0.1700
Data Index: 220454 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8053. Min Act: -0.1700
Data Index: 1542245 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7894. Min Act: -0.1700
Data Index: 4545941 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8053. Min Act: -0.1700
Data Index: 6902369 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7894. Min Act: -0.1700
Data Index: 5666480 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8212. Min Act: -0.1700
Data Index: 1733828 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8371. Min Act: -0.1700
Data Index: 6296780 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.8053. Min Act: -0.1700
Data Index: 3452685 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7894. Min Act: -0.1700
Data Index: 8590012 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7575. Min Act: -0.1700
Data Index: 2100657 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7575. Min Act: -0.1700
Data Index: 4321415 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7734. Min Act: -0.1700
Data Index: 7794624 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7415. Min Act: -0.1700
Data Index: 7091025 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7255. Min Act: -0.1700
Data Index: 2025431 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7415. Min Act: -0.1700
Data Index: 8458446 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8848. Min Range: -2.8848
Max Act: 2.7095. Min Act: -0.1700
Data Index: 6870841 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19