Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.7509. Min Act: -0.1700
Data Index: 859413 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.7821. Min Act: -0.1700
Data Index: 4626453 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.7196. Min Act: -0.1700
Data Index: 3058168 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.7196. Min Act: -0.1700
Data Index: 3455127 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.6571. Min Act: -0.1700
Data Index: 794274 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.6884. Min Act: -0.1700
Data Index: 5419604 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.6571. Min Act: -0.1700
Data Index: 1534681 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.6884. Min Act: -0.1700
Data Index: 6270609 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5634. Min Act: -0.1700
Data Index: 2603586 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.6259. Min Act: -0.1700
Data Index: 7734243 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.6259. Min Act: -0.1700
Data Index: 1757724 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5946. Min Act: -0.1700
Data Index: 106532 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5946. Min Act: -0.1700
Data Index: 6301685 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5946. Min Act: -0.1700
Data Index: 1004473 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5634. Min Act: -0.1700
Data Index: 8144929 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5946. Min Act: -0.1700
Data Index: 3698316 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5321. Min Act: -0.1700
Data Index: 6512907 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5321. Min Act: -0.1700
Data Index: 7346636 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5946. Min Act: -0.1700
Data Index: 635117 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7821. Min Range: -4.7821
Max Act: 4.5634. Min Act: -0.1700
Data Index: 7803260 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19