Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4664 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.6856. Min Act: -0.1700
Data Index: 8765141 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.6230. Min Act: -0.1700
Data Index: 8394328 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.5917. Min Act: -0.1700
Data Index: 6927034 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.5760. Min Act: -0.1700
Data Index: 4407758 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.5134. Min Act: -0.1700
Data Index: 2871872 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.5134. Min Act: -0.1700
Data Index: 4440012 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.5291. Min Act: -0.1700
Data Index: 2588406 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.5134. Min Act: -0.1700
Data Index: 2070856 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4821. Min Act: -0.1700
Data Index: 1862827 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4664. Min Act: -0.1700
Data Index: 8068654 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4664. Min Act: -0.1700
Data Index: 8085774 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4821. Min Act: -0.1700
Data Index: 32620 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4351. Min Act: -0.1700
Data Index: 6033411 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4507. Min Act: -0.1700
Data Index: 5898614 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4351. Min Act: -0.1700
Data Index: 846297 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4507. Min Act: -0.1700
Data Index: 3737900 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4194. Min Act: -0.1700
Data Index: 1932399 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4037. Min Act: -0.1700
Data Index: 6486097 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4037. Min Act: -0.1700
Data Index: 6940230 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6856. Min Range: -3.6856
Max Act: 3.4194. Min Act: -0.1700
Data Index: 3982010 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19