Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0171. Min Range: -5.0171
Max Act: 5.0171. Min Act: -0.1700
Data Index: 994236 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0171. Min Range: -5.0171
Max Act: 5.0171. Min Act: -0.1700
Data Index: 3261575 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.9546. Min Act: -0.1700
Data Index: 3341773 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.9233. Min Act: -0.1700
Data Index: 6934000 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.9233. Min Act: -0.1700
Data Index: 4745860 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.8921. Min Act: -0.1700
Data Index: 1418689 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.8921. Min Act: -0.1700
Data Index: 4350165 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.8608. Min Act: -0.1700
Data Index: 7574298 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.8608. Min Act: -0.1700
Data Index: 5999214 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.8608. Min Act: -0.1700
Data Index: 3495594 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.8608. Min Act: -0.1700
Data Index: 7584776 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7983. Min Act: -0.1700
Data Index: 3396102 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.8296. Min Act: -0.1700
Data Index: 5512234 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7358. Min Act: -0.1700
Data Index: 7729044 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7671. Min Act: -0.1700
Data Index: 8812279 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7983. Min Act: -0.1700
Data Index: 8754733 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7671. Min Act: -0.1700
Data Index: 1207471 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7671. Min Act: -0.1700
Data Index: 1642985 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7358. Min Act: -0.1700
Data Index: 5940011 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7671. Min Act: -0.1700
Data Index: 790310 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19