Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6791. Min Range: -7.6791
Max Act: 7.6791. Min Act: -0.1700
Data Index: 8773372 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.8978. Min Act: -0.1700
Data Index: 7594777 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.8978. Min Act: -0.1700
Data Index: 2807576 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.8666. Min Act: -0.1700
Data Index: 6186280 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.8666. Min Act: -0.1700
Data Index: 1649193 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.8666. Min Act: -0.1700
Data Index: 5232182 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.8041. Min Act: -0.1700
Data Index: 4226386 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.8353. Min Act: -0.1700
Data Index: 8144739 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.8041. Min Act: -0.1700
Data Index: 7594778 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.6478. Min Act: -0.1700
Data Index: 7544160 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.6478. Min Act: -0.1700
Data Index: 5951540 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.6478. Min Act: -0.1700
Data Index: 284577 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.6166. Min Act: -0.1700
Data Index: 929886 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.5541. Min Act: -0.1700
Data Index: 8773374 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.5541. Min Act: -0.1700
Data Index: 2358740 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.5228. Min Act: -0.1700
Data Index: 7517671 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.5228. Min Act: -0.1700
Data Index: 73268 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.4916. Min Act: -0.1700
Data Index: 2807586 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.4603. Min Act: -0.1700
Data Index: 2634399 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6791. Min Range: -7.6791
Max Act: 6.4603. Min Act: -0.1700
Data Index: 5951238 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19