Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4374 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.5288. Min Act: -0.1700
Data Index: 887280 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.5288. Min Act: -0.1700
Data Index: 3916494 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.5288. Min Act: -0.1700
Data Index: 8710276 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.4350. Min Act: -0.1700
Data Index: 7301191 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.2475. Min Act: -0.1700
Data Index: 3546482 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.2163. Min Act: -0.1700
Data Index: 5422299 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.1850. Min Act: -0.1700
Data Index: 2664971 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.1850. Min Act: -0.1700
Data Index: 2403974 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.1538. Min Act: -0.1700
Data Index: 2399100 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.1225. Min Act: -0.1700
Data Index: 487443 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.1538. Min Act: -0.1700
Data Index: 7803701 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.1225. Min Act: -0.1700
Data Index: 1012828 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.0913. Min Act: -0.1700
Data Index: 3992648 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.0600. Min Act: -0.1700
Data Index: 3652801 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.0600. Min Act: -0.1700
Data Index: 5692981 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.0288. Min Act: -0.1700
Data Index: 8140880 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.0600. Min Act: -0.1700
Data Index: 2493919 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.0288. Min Act: -0.1700
Data Index: 1559745 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5288. Min Range: -6.5288
Max Act: 6.0288. Min Act: -0.1700
Data Index: 3269502 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5288. Min Range: -6.5288
Max Act: 5.9975. Min Act: -0.1700
Data Index: 3466438 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19