Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1521. Min Range: -6.1521
Max Act: 6.1521. Min Act: -0.1700
Data Index: 8142280 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.9334. Min Act: -0.1700
Data Index: 2064315 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.8396. Min Act: -0.1700
Data Index: 8284184 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.8396. Min Act: -0.1700
Data Index: 281198 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.8396. Min Act: -0.1700
Data Index: 1002455 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.8084. Min Act: -0.1700
Data Index: 7656349 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.7771. Min Act: -0.1700
Data Index: 4216034 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.7771. Min Act: -0.1700
Data Index: 4114436 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.7459. Min Act: -0.1700
Data Index: 2301856 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.7459. Min Act: -0.1700
Data Index: 5046396 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.7459. Min Act: -0.1700
Data Index: 2198364 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.6834. Min Act: -0.1700
Data Index: 6810691 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.5896. Min Act: -0.1700
Data Index: 3919274 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.5896. Min Act: -0.1700
Data Index: 3912357 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.5584. Min Act: -0.1700
Data Index: 8258335 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.5584. Min Act: -0.1700
Data Index: 6342705 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.5584. Min Act: -0.1700
Data Index: 1833497 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.5584. Min Act: -0.1700
Data Index: 1652290 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.5584. Min Act: -0.1700
Data Index: 5825288 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1521. Min Range: -6.1521
Max Act: 5.5896. Min Act: -0.1700
Data Index: 725247 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19