Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.8541. Min Act: -0.1700
Data Index: 8452455 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.7603. Min Act: -0.1700
Data Index: 1008752 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.7916. Min Act: -0.1700
Data Index: 1295943 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.7916. Min Act: -0.1700
Data Index: 1315181 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.7916. Min Act: -0.1700
Data Index: 6009135 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.7603. Min Act: -0.1700
Data Index: 2677312 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.7603. Min Act: -0.1700
Data Index: 914909 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.7603. Min Act: -0.1700
Data Index: 8072667 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.7291. Min Act: -0.1700
Data Index: 5491826 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.7291. Min Act: -0.1700
Data Index: 2265095 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6978. Min Act: -0.1700
Data Index: 4698063 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6978. Min Act: -0.1700
Data Index: 2030553 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6978. Min Act: -0.1700
Data Index: 3152114 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6666. Min Act: -0.1700
Data Index: 694139 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6666. Min Act: -0.1700
Data Index: 5921645 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6666. Min Act: -0.1700
Data Index: 6491419 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6353. Min Act: -0.1700
Data Index: 1049254 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6353. Min Act: -0.1700
Data Index: 3305103 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6353. Min Act: -0.1700
Data Index: 2677313 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8541. Min Range: -5.8541
Max Act: 5.6041. Min Act: -0.1700
Data Index: 7194675 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19