Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1671 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.5735. Min Act: -0.1700
Data Index: 8433733 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.5423. Min Act: -0.1700
Data Index: 7770633 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.5423. Min Act: -0.1700
Data Index: 3806270 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.4173. Min Act: -0.1700
Data Index: 2498323 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.2610. Min Act: -0.1700
Data Index: 5142275 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.1360. Min Act: -0.1700
Data Index: 7045275 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.1360. Min Act: -0.1700
Data Index: 2862868 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.1048. Min Act: -0.1700
Data Index: 4701261 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.1048. Min Act: -0.1700
Data Index: 835780 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.1048. Min Act: -0.1700
Data Index: 4762478 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.0735. Min Act: -0.1700
Data Index: 7289645 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.0110. Min Act: -0.1700
Data Index: 3247513 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.0110. Min Act: -0.1700
Data Index: 8568901 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.0110. Min Act: -0.1700
Data Index: 1364816 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5735. Min Range: -7.5735
Max Act: 6.9485. Min Act: -0.1700
Data Index: 3561170 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5735. Min Range: -7.5735
Max Act: 7.0110. Min Act: -0.1700
Data Index: 8463489 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5735. Min Range: -7.5735
Max Act: 6.9798. Min Act: -0.1700
Data Index: 1191988 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5735. Min Range: -7.5735
Max Act: 6.9485. Min Act: -0.1700
Data Index: 1711578 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5735. Min Range: -7.5735
Max Act: 6.9485. Min Act: -0.1700
Data Index: 8443948 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5735. Min Range: -7.5735
Max Act: 6.9485. Min Act: -0.1700
Data Index: 7454500 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19