Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.5520. Min Act: -0.1700
Data Index: 8593812 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.5207. Min Act: -0.1700
Data Index: 8649069 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.4270. Min Act: -0.1700
Data Index: 3108894 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.3645. Min Act: -0.1700
Data Index: 5973161 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.3332. Min Act: -0.1700
Data Index: 5938424 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.2707. Min Act: -0.1700
Data Index: 6146094 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.1457. Min Act: -0.1700
Data Index: 8081162 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.1145. Min Act: -0.1700
Data Index: 7004343 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.1145. Min Act: -0.1700
Data Index: 4625185 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.0832. Min Act: -0.1700
Data Index: 8594793 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.0832. Min Act: -0.1700
Data Index: 1911567 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.0832. Min Act: -0.1700
Data Index: 174097 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.0520. Min Act: -0.1700
Data Index: 297438 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.0207. Min Act: -0.1700
Data Index: 2734115 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5520. Min Range: -7.5520
Max Act: 7.0520. Min Act: -0.1700
Data Index: 5756785 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5520. Min Range: -7.5520
Max Act: 6.9895. Min Act: -0.1700
Data Index: 737921 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5520. Min Range: -7.5520
Max Act: 6.9895. Min Act: -0.1700
Data Index: 5328399 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5520. Min Range: -7.5520
Max Act: 6.9582. Min Act: -0.1700
Data Index: 6513150 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5520. Min Range: -7.5520
Max Act: 6.9270. Min Act: -0.1700
Data Index: 895344 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5520. Min Range: -7.5520
Max Act: 6.9270. Min Act: -0.1700
Data Index: 6740643 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19