Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 6502202 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 5559422 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 4483599 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 7383777 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 7612653 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 8186343 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1352666 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 2254593 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 5250218 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.6044. Min Act: -0.1700
Data Index: 743915 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.5560. Min Act: -0.1700
Data Index: 6747497 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.5237. Min Act: -0.1700
Data Index: 1741279 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.5075. Min Act: -0.1700
Data Index: 1527822 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.4913. Min Act: -0.1700
Data Index: 5446869 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.4263. Min Act: -0.1700
Data Index: 2261144 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.4263. Min Act: -0.1700
Data Index: 457573 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.4263. Min Act: -0.1700
Data Index: 5820613 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.4263. Min Act: -0.1700
Data Index: 5176918 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.4263. Min Act: -0.1700
Data Index: 2135655 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6044. Min Range: -2.6044
Max Act: 2.4263. Min Act: -0.1700
Data Index: 1770540 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19