Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1324 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.3088. Min Act: -0.1700
Data Index: 1186145 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.3252. Min Act: -0.1700
Data Index: 5132954 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.2097. Min Act: -0.1700
Data Index: 7653373 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.2097. Min Act: -0.1700
Data Index: 7217057 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.1765. Min Act: -0.1700
Data Index: 2553653 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.1432. Min Act: -0.1700
Data Index: 4978987 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.1098. Min Act: -0.1700
Data Index: 7393348 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0931. Min Act: -0.1700
Data Index: 8574437 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0931. Min Act: -0.1700
Data Index: 766602 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0931. Min Act: -0.1700
Data Index: 24676 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0595. Min Act: -0.1700
Data Index: 7536524 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0595. Min Act: -0.1700
Data Index: 7349188 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0427. Min Act: -0.1700
Data Index: 791405 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0427. Min Act: -0.1700
Data Index: 6096747 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0427. Min Act: -0.1700
Data Index: 5873136 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0427. Min Act: -0.1700
Data Index: 7697031 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0258. Min Act: -0.1700
Data Index: 3659668 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3252. Min Range: -2.3252
Max Act: 1.9921. Min Act: -0.1700
Data Index: 6486429 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0090. Min Act: -0.1699
Data Index: 4263589 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3252. Min Range: -2.3252
Max Act: 2.0258. Min Act: -0.1700
Data Index: 4494608 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19