Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4102 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.7207. Min Act: -0.1700
Data Index: 582230 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.6582. Min Act: -0.1700
Data Index: 4598487 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.5332. Min Act: -0.1700
Data Index: 1450342 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.4395. Min Act: -0.1700
Data Index: 6083880 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.4395. Min Act: -0.1700
Data Index: 8149195 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.4082. Min Act: -0.1700
Data Index: 46938 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.3770. Min Act: -0.1700
Data Index: 5666702 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.3457. Min Act: -0.1700
Data Index: 6628197 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.3145. Min Act: -0.1700
Data Index: 6249197 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.2832. Min Act: -0.1700
Data Index: 1756236 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.2832. Min Act: -0.1700
Data Index: 2031276 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.3145. Min Act: -0.1700
Data Index: 5322823 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.2520. Min Act: -0.1700
Data Index: 5737162 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.2207. Min Act: -0.1700
Data Index: 1773881 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.2207. Min Act: -0.1700
Data Index: 2444376 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.1895. Min Act: -0.1700
Data Index: 7249782 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.1582. Min Act: -0.1700
Data Index: 7410732 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.1582. Min Act: -0.1700
Data Index: 4698418 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.1270. Min Act: -0.1700
Data Index: 667022 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7207. Min Range: -7.7207
Max Act: 7.1582. Min Act: -0.1700
Data Index: 111796 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19