Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1912. Min Range: -6.1912
Max Act: 6.1912. Min Act: -0.1700
Data Index: 1615925 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1912. Min Range: -6.1912
Max Act: 6.1600. Min Act: -0.1700
Data Index: 2253679 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1912. Min Range: -6.1912
Max Act: 6.1287. Min Act: -0.1700
Data Index: 3116176 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1912. Min Range: -6.1912
Max Act: 6.0975. Min Act: -0.1700
Data Index: 106617 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1912. Min Range: -6.1912
Max Act: 6.0350. Min Act: -0.1700
Data Index: 3197398 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1912. Min Range: -6.1912
Max Act: 6.0350. Min Act: -0.1700
Data Index: 5745912 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1912. Min Range: -6.1912
Max Act: 6.0350. Min Act: -0.1700
Data Index: 8116051 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.9100. Min Act: -0.1700
Data Index: 3752063 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.9412. Min Act: -0.1700
Data Index: 8450672 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.9100. Min Act: -0.1700
Data Index: 2791304 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.8787. Min Act: -0.1700
Data Index: 4318461 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.8475. Min Act: -0.1700
Data Index: 6083199 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.8162. Min Act: -0.1700
Data Index: 5116505 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.7850. Min Act: -0.1700
Data Index: 2700470 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.7850. Min Act: -0.1700
Data Index: 295961 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.7537. Min Act: -0.1700
Data Index: 3715608 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.7537. Min Act: -0.1700
Data Index: 6797131 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.7537. Min Act: -0.1700
Data Index: 5405212 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.7537. Min Act: -0.1700
Data Index: 3891404 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1912. Min Range: -6.1912
Max Act: 5.7537. Min Act: -0.1700
Data Index: 2001038 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19