Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1664 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.4712. Min Act: -0.1700
Data Index: 7967533 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.4399. Min Act: -0.1700
Data Index: 7196910 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.4399. Min Act: -0.1700
Data Index: 8578098 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.4399. Min Act: -0.1700
Data Index: 3420540 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.3462. Min Act: -0.1700
Data Index: 4282898 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.3774. Min Act: -0.1700
Data Index: 4916263 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.3149. Min Act: -0.1700
Data Index: 6930428 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.3462. Min Act: -0.1700
Data Index: 5544776 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.3774. Min Act: -0.1700
Data Index: 6778499 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.3462. Min Act: -0.1700
Data Index: 5437770 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.3149. Min Act: -0.1700
Data Index: 7896758 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.3149. Min Act: -0.1700
Data Index: 5305686 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.2837. Min Act: -0.1700
Data Index: 5006212 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.2837. Min Act: -0.1700
Data Index: 3959592 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.2837. Min Act: -0.1700
Data Index: 2740088 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.2524. Min Act: -0.1700
Data Index: 3435573 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.1899. Min Act: -0.1700
Data Index: 211380 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.2524. Min Act: -0.1700
Data Index: 2676526 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.2524. Min Act: -0.1700
Data Index: 2968683 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4712. Min Range: -5.4712
Max Act: 5.2524. Min Act: -0.1700
Data Index: 5318452 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19