Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.2057. Min Act: -0.1700
Data Index: 3544454 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0807. Min Act: -0.1700
Data Index: 8212317 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8932. Min Act: -0.1700
Data Index: 686048 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8932. Min Act: -0.1700
Data Index: 6127503 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8307. Min Act: -0.1700
Data Index: 6138731 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8620. Min Act: -0.1700
Data Index: 8082242 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8307. Min Act: -0.1700
Data Index: 6553679 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8307. Min Act: -0.1700
Data Index: 8832338 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8307. Min Act: -0.1700
Data Index: 1396911 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8307. Min Act: -0.1700
Data Index: 7194112 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7682. Min Act: -0.1700
Data Index: 7321247 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7682. Min Act: -0.1700
Data Index: 7326490 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7682. Min Act: -0.1700
Data Index: 6119403 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7682. Min Act: -0.1700
Data Index: 1049773 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7370. Min Act: -0.1700
Data Index: 6648053 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7370. Min Act: -0.1700
Data Index: 4462488 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7057. Min Act: -0.1700
Data Index: 1136096 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.6745. Min Act: -0.1700
Data Index: 7270098 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.6745. Min Act: -0.1700
Data Index: 6394681 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7057. Min Act: -0.1700
Data Index: 1776459 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19