Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.8612. Min Act: -0.1700
Data Index: 7420458 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.8294. Min Act: -0.1700
Data Index: 4427350 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.7338. Min Act: -0.1700
Data Index: 4572309 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.7498. Min Act: -0.1700
Data Index: 8611933 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.7338. Min Act: -0.1700
Data Index: 5882424 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6858. Min Act: -0.1700
Data Index: 6928724 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6538. Min Act: -0.1700
Data Index: 3792159 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6698. Min Act: -0.1700
Data Index: 8611932 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6698. Min Act: -0.1700
Data Index: 6007994 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6538. Min Act: -0.1700
Data Index: 4334944 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6538. Min Act: -0.1700
Data Index: 2934816 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6377. Min Act: -0.1700
Data Index: 8696564 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6217. Min Act: -0.1700
Data Index: 3141284 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6377. Min Act: -0.1700
Data Index: 2576904 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6217. Min Act: -0.1700
Data Index: 2864081 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6056. Min Act: -0.1700
Data Index: 1752526 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.6056. Min Act: -0.1700
Data Index: 4435050 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.5895. Min Act: -0.1700
Data Index: 799855 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.5895. Min Act: -0.1700
Data Index: 2709538 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8612. Min Range: -2.8612
Max Act: 2.5895. Min Act: -0.1700
Data Index: 6245172 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19