Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.5420. Min Act: -0.1700
Data Index: 6272525 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.3383. Min Act: -0.1700
Data Index: 8140549 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.2441. Min Act: -0.1700
Data Index: 4347247 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.1812. Min Act: -0.1700
Data Index: 8041832 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.1812. Min Act: -0.1700
Data Index: 7533927 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.1654. Min Act: -0.1700
Data Index: 2910694 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.1339. Min Act: -0.1700
Data Index: 7305022 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.1339. Min Act: -0.1700
Data Index: 4878809 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.1024. Min Act: -0.1700
Data Index: 5325433 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0709. Min Act: -0.1700
Data Index: 5653793 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0709. Min Act: -0.1700
Data Index: 518825 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0709. Min Act: -0.1700
Data Index: 2713742 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0709. Min Act: -0.1700
Data Index: 3553962 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0709. Min Act: -0.1700
Data Index: 7539852 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0551. Min Act: -0.1700
Data Index: 1775128 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0551. Min Act: -0.1700
Data Index: 738267 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0551. Min Act: -0.1700
Data Index: 1881213 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0236. Min Act: -0.1700
Data Index: 5371951 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0078. Min Act: -0.1700
Data Index: 8051796 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5420. Min Range: -3.5420
Max Act: 3.0236. Min Act: -0.1700
Data Index: 7225380 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19