Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 725 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.6210. Min Act: -0.1700
Data Index: 6725022 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.4647. Min Act: -0.1700
Data Index: 1095876 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.4335. Min Act: -0.1700
Data Index: 5181656 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.4335. Min Act: -0.1700
Data Index: 8419064 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.4022. Min Act: -0.1700
Data Index: 2791227 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.4022. Min Act: -0.1700
Data Index: 8398045 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.4022. Min Act: -0.1700
Data Index: 154288 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.3710. Min Act: -0.1700
Data Index: 3681087 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.4022. Min Act: -0.1700
Data Index: 8603474 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.4022. Min Act: -0.1700
Data Index: 5181655 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.3710. Min Act: -0.1700
Data Index: 6468619 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.3710. Min Act: -0.1700
Data Index: 5552693 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.3397. Min Act: -0.1700
Data Index: 4362963 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.3397. Min Act: -0.1700
Data Index: 4567793 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.3397. Min Act: -0.1700
Data Index: 2804083 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.3397. Min Act: -0.1700
Data Index: 2047411 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.3085. Min Act: -0.1700
Data Index: 5412789 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.2772. Min Act: -0.1700
Data Index: 6731095 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.2772. Min Act: -0.1700
Data Index: 8551943 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6210. Min Range: -4.6210
Max Act: 4.2772. Min Act: -0.1700
Data Index: 5774505 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19