Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1950 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.3642. Min Act: -0.1700
Data Index: 7207703 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.2704. Min Act: -0.1700
Data Index: 4170169 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.1767. Min Act: -0.1700
Data Index: 2132807 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.1142. Min Act: -0.1700
Data Index: 3465649 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.1454. Min Act: -0.1700
Data Index: 1545165 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.1142. Min Act: -0.1700
Data Index: 8355547 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.0829. Min Act: -0.1700
Data Index: 412555 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.1142. Min Act: -0.1700
Data Index: 3370577 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.0517. Min Act: -0.1700
Data Index: 5996462 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.0204. Min Act: -0.1700
Data Index: 4057354 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.0517. Min Act: -0.1700
Data Index: 751610 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.0517. Min Act: -0.1700
Data Index: 5872705 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3642. Min Range: -6.3642
Max Act: 6.0204. Min Act: -0.1700
Data Index: 2132028 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3642. Min Range: -6.3642
Max Act: 5.9892. Min Act: -0.1700
Data Index: 7207702 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3642. Min Range: -6.3642
Max Act: 5.9892. Min Act: -0.1700
Data Index: 7303615 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3642. Min Range: -6.3642
Max Act: 5.9892. Min Act: -0.1700
Data Index: 5352452 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3642. Min Range: -6.3642
Max Act: 5.9267. Min Act: -0.1700
Data Index: 2522956 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3642. Min Range: -6.3642
Max Act: 5.8954. Min Act: -0.1700
Data Index: 3756483 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3642. Min Range: -6.3642
Max Act: 5.9579. Min Act: -0.1699
Data Index: 4279854 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3642. Min Range: -6.3642
Max Act: 5.8954. Min Act: -0.1700
Data Index: 6072180 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19