Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1621 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.3921. Min Act: -0.1700
Data Index: 3884013 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.3921. Min Act: -0.1700
Data Index: 7480927 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.2359. Min Act: -0.1700
Data Index: 2029242 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.1734. Min Act: -0.1700
Data Index: 5269858 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.1421. Min Act: -0.1700
Data Index: 666234 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.1421. Min Act: -0.1700
Data Index: 8257330 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.1109. Min Act: -0.1700
Data Index: 7115705 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.1109. Min Act: -0.1700
Data Index: 8267669 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.0796. Min Act: -0.1700
Data Index: 2671528 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.1109. Min Act: -0.1700
Data Index: 2059933 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.0171. Min Act: -0.1700
Data Index: 3670973 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.0484. Min Act: -0.1700
Data Index: 4638012 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.0484. Min Act: -0.1700
Data Index: 2132427 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.0484. Min Act: -0.1700
Data Index: 4713072 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.0171. Min Act: -0.1700
Data Index: 7645473 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.0484. Min Act: -0.1700
Data Index: 8302820 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3921. Min Range: -6.3921
Max Act: 6.0171. Min Act: -0.1700
Data Index: 169736 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3921. Min Range: -6.3921
Max Act: 5.9859. Min Act: -0.1700
Data Index: 1784600 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3921. Min Range: -6.3921
Max Act: 5.9546. Min Act: -0.1700
Data Index: 5016984 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3921. Min Range: -6.3921
Max Act: 5.9546. Min Act: -0.1700
Data Index: 3830369 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19