Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4983 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.8174. Min Act: -0.1700
Data Index: 6046768 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.7549. Min Act: -0.1700
Data Index: 3599727 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.6299. Min Act: -0.1700
Data Index: 325888 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.5674. Min Act: -0.1700
Data Index: 1986698 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.5674. Min Act: -0.1700
Data Index: 856493 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.4424. Min Act: -0.1700
Data Index: 3943057 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3799. Min Act: -0.1700
Data Index: 2946959 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3799. Min Act: -0.1700
Data Index: 1488275 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3799. Min Act: -0.1700
Data Index: 5561125 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3799. Min Act: -0.1700
Data Index: 4641857 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3799. Min Act: -0.1700
Data Index: 1484887 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3799. Min Act: -0.1700
Data Index: 2619818 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3799. Min Act: -0.1700
Data Index: 6586717 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3799. Min Act: -0.1700
Data Index: 5618857 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3174. Min Act: -0.1700
Data Index: 5578659 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3799. Min Act: -0.1700
Data Index: 4570895 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3174. Min Act: -0.1700
Data Index: 2559045 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3174. Min Act: -0.1700
Data Index: 3670760 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3174. Min Act: -0.1700
Data Index: 4856092 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8174. Min Range: -9.8174
Max Act: 9.3174. Min Act: -0.1700
Data Index: 5112483 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19