Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.7299. Min Act: -0.1700
Data Index: 1416857 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.7299. Min Act: -0.1700
Data Index: 3482145 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6986. Min Act: -0.1700
Data Index: 5294368 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.7611. Min Act: -0.1700
Data Index: 3818317 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.7299. Min Act: -0.1700
Data Index: 5153677 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.7299. Min Act: -0.1700
Data Index: 2848440 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6361. Min Act: -0.1700
Data Index: 730818 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6674. Min Act: -0.1700
Data Index: 2424451 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6674. Min Act: -0.1700
Data Index: 1503029 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6049. Min Act: -0.1700
Data Index: 2619824 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6361. Min Act: -0.1700
Data Index: 424995 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6361. Min Act: -0.1700
Data Index: 2901862 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.5736. Min Act: -0.1700
Data Index: 4688448 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6674. Min Act: -0.1700
Data Index: 1323246 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6049. Min Act: -0.1700
Data Index: 2565488 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.6049. Min Act: -0.1700
Data Index: 5726668 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.5424. Min Act: -0.1700
Data Index: 1868070 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.5424. Min Act: -0.1700
Data Index: 7040611 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.5736. Min Act: -0.1700
Data Index: 6688750 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7611. Min Range: -4.7611
Max Act: 4.5424. Min Act: -0.1700
Data Index: 1235467 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19