Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.1275. Min Act: -0.1700
Data Index: 624799 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.0960. Min Act: -0.1700
Data Index: 6476756 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.0487. Min Act: -0.1700
Data Index: 7637613 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.0645. Min Act: -0.1700
Data Index: 3344819 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.0013. Min Act: -0.1700
Data Index: 1527234 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.0171. Min Act: -0.1700
Data Index: 2267528 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.0171. Min Act: -0.1700
Data Index: 6467204 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.0013. Min Act: -0.1700
Data Index: 148061 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.0013. Min Act: -0.1700
Data Index: 4624747 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9697. Min Act: -0.1700
Data Index: 1650073 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9855. Min Act: -0.1700
Data Index: 4340491 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9381. Min Act: -0.1700
Data Index: 2045816 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9697. Min Act: -0.1700
Data Index: 7423247 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9539. Min Act: -0.1700
Data Index: 5237588 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1275. Min Range: -3.1275
Max Act: 3.0013. Min Act: -0.1700
Data Index: 197181 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9381. Min Act: -0.1700
Data Index: 164237 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9381. Min Act: -0.1700
Data Index: 8459326 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9697. Min Act: -0.1700
Data Index: 3333050 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9381. Min Act: -0.1700
Data Index: 5788238 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1275. Min Range: -3.1275
Max Act: 2.9222. Min Act: -0.1700
Data Index: 3068573 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19