Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2603 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.6301. Min Act: -0.1700
Data Index: 4125418 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.4739. Min Act: -0.1700
Data Index: 21925 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.4426. Min Act: -0.1700
Data Index: 6084026 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.3489. Min Act: -0.1700
Data Index: 2747769 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.3489. Min Act: -0.1700
Data Index: 5182907 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.3176. Min Act: -0.1700
Data Index: 807866 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.2551. Min Act: -0.1700
Data Index: 1831301 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.2551. Min Act: -0.1700
Data Index: 7266257 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.2239. Min Act: -0.1700
Data Index: 2300540 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.1614. Min Act: -0.1700
Data Index: 5678997 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.1614. Min Act: -0.1700
Data Index: 3402570 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.1614. Min Act: -0.1700
Data Index: 1773745 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.1301. Min Act: -0.1700
Data Index: 7691802 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.1301. Min Act: -0.1700
Data Index: 4861793 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.0676. Min Act: -0.1700
Data Index: 3003219 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.0989. Min Act: -0.1700
Data Index: 8313118 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.0676. Min Act: -0.1700
Data Index: 7246663 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.0676. Min Act: -0.1700
Data Index: 6572803 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.0676. Min Act: -0.1700
Data Index: 5298867 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6301. Min Range: -6.6301
Max Act: 6.0676. Min Act: -0.1700
Data Index: 5229425 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19