Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.5686. Min Act: -0.1700
Data Index: 8509722 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.5529. Min Act: -0.1700
Data Index: 2546323 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4903. Min Act: -0.1700
Data Index: 1383179 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4903. Min Act: -0.1700
Data Index: 4790242 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4589. Min Act: -0.1700
Data Index: 2107965 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4746. Min Act: -0.1700
Data Index: 5850814 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4433. Min Act: -0.1700
Data Index: 4091831 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4589. Min Act: -0.1700
Data Index: 2776692 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4589. Min Act: -0.1700
Data Index: 8818354 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4433. Min Act: -0.1700
Data Index: 718362 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4433. Min Act: -0.1700
Data Index: 3544074 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4433. Min Act: -0.1700
Data Index: 7657829 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4433. Min Act: -0.1700
Data Index: 5944136 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4276. Min Act: -0.1700
Data Index: 7127611 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4433. Min Act: -0.1700
Data Index: 3580667 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4119. Min Act: -0.1700
Data Index: 621690 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4276. Min Act: -0.1700
Data Index: 1748899 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4276. Min Act: -0.1700
Data Index: 8214322 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4276. Min Act: -0.1700
Data Index: 4892535 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4276. Min Act: -0.1700
Data Index: 3005674 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19