Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1766 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2983. Min Range: -5.2983
Max Act: 5.2983. Min Act: -0.1700
Data Index: 2269081 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2983. Min Range: -5.2983
Max Act: 5.0796. Min Act: -0.1700
Data Index: 2269076 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2983. Min Range: -5.2983
Max Act: 5.0483. Min Act: -0.1700
Data Index: 2269075 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.9546. Min Act: -0.1700
Data Index: 7683405 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.8921. Min Act: -0.1700
Data Index: 3060037 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.8608. Min Act: -0.1700
Data Index: 6105630 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7983. Min Act: -0.1700
Data Index: 2269077 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.8296. Min Act: -0.1700
Data Index: 2269080 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.8296. Min Act: -0.1700
Data Index: 2269078 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7983. Min Act: -0.1700
Data Index: 7813471 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7983. Min Act: -0.1700
Data Index: 7066398 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7983. Min Act: -0.1700
Data Index: 2269079 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7983. Min Act: -0.1700
Data Index: 2269074 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7671. Min Act: -0.1700
Data Index: 3659495 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7358. Min Act: -0.1700
Data Index: 6124079 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7358. Min Act: -0.1700
Data Index: 367122 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7358. Min Act: -0.1700
Data Index: 3659494 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7358. Min Act: -0.1700
Data Index: 5556975 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.7046. Min Act: -0.1700
Data Index: 6715988 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2983. Min Range: -5.2983
Max Act: 4.6733. Min Act: -0.1700
Data Index: 7683408 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19