Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 506 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.4759. Min Act: -0.1700
Data Index: 4465394 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.4446. Min Act: -0.1700
Data Index: 4573943 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.4134. Min Act: -0.1700
Data Index: 7392570 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.3821. Min Act: -0.1700
Data Index: 3142330 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.3821. Min Act: -0.1700
Data Index: 4658062 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.3509. Min Act: -0.1700
Data Index: 8428004 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.3509. Min Act: -0.1700
Data Index: 6184144 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.3196. Min Act: -0.1700
Data Index: 20527 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.3196. Min Act: -0.1700
Data Index: 5177232 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.3196. Min Act: -0.1700
Data Index: 5532180 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2884. Min Act: -0.1700
Data Index: 275596 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2884. Min Act: -0.1700
Data Index: 7645194 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2884. Min Act: -0.1700
Data Index: 8569546 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2884. Min Act: -0.1700
Data Index: 4429294 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2884. Min Act: -0.1700
Data Index: 2366598 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2884. Min Act: -0.1700
Data Index: 431872 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2571. Min Act: -0.1700
Data Index: 5033135 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2571. Min Act: -0.1700
Data Index: 2471162 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2571. Min Act: -0.1700
Data Index: 5443726 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4759. Min Range: -5.4759
Max Act: 5.2571. Min Act: -0.1700
Data Index: 2878190 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19