Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4819 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3992. Min Act: -0.1700
Data Index: 6872581 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3680. Min Act: -0.1700
Data Index: 1077316 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3992. Min Act: -0.1700
Data Index: 6950035 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3367. Min Act: -0.1700
Data Index: 3935633 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3367. Min Act: -0.1700
Data Index: 3513934 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3367. Min Act: -0.1700
Data Index: 1751447 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3367. Min Act: -0.1700
Data Index: 7688925 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3055. Min Act: -0.1700
Data Index: 1684714 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3055. Min Act: -0.1691
Data Index: 2835966 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3055. Min Act: -0.1691
Data Index: 235562 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3055. Min Act: -0.1700
Data Index: 6402712 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3055. Min Act: -0.1700
Data Index: 4686721 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.2742. Min Act: -0.1700
Data Index: 1077318 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3055. Min Act: -0.1700
Data Index: 1077324 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.3055. Min Act: -0.1700
Data Index: 1077323 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.2742. Min Act: -0.1700
Data Index: 1077327 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.2742. Min Act: -0.1700
Data Index: 1077329 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.2742. Min Act: -0.1700
Data Index: 2051901 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.2742. Min Act: -0.1700
Data Index: 3034904 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3992. Min Range: -6.3992
Max Act: 6.2742. Min Act: -0.1700
Data Index: 2202521 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19