Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 141 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1479. Min Range: -6.1479
Max Act: 6.1479. Min Act: -0.1700
Data Index: 4158685 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1479. Min Range: -6.1479
Max Act: 6.0854. Min Act: -0.1700
Data Index: 3847149 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1479. Min Range: -6.1479
Max Act: 6.0542. Min Act: -0.1700
Data Index: 6236888 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1479. Min Range: -6.1479
Max Act: 6.0542. Min Act: -0.1700
Data Index: 4888474 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1479. Min Range: -6.1479
Max Act: 6.0229. Min Act: -0.1700
Data Index: 7553728 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.9917. Min Act: -0.1700
Data Index: 1808701 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.9917. Min Act: -0.1700
Data Index: 8598673 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.9292. Min Act: -0.1700
Data Index: 2371447 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.8979. Min Act: -0.1700
Data Index: 1035563 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.8667. Min Act: -0.1700
Data Index: 2706282 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.8667. Min Act: -0.1700
Data Index: 7877863 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.8667. Min Act: -0.1700
Data Index: 4890189 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.8667. Min Act: -0.1700
Data Index: 4610052 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.8354. Min Act: -0.1700
Data Index: 7583785 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.8354. Min Act: -0.1700
Data Index: 3942373 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.8354. Min Act: -0.1700
Data Index: 7482666 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.8354. Min Act: -0.1700
Data Index: 2245300 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.7417. Min Act: -0.1700
Data Index: 1170057 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.7417. Min Act: -0.1700
Data Index: 4676086 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1479. Min Range: -6.1479
Max Act: 5.7417. Min Act: -0.1700
Data Index: 5619159 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19