Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4677 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.2358. Min Act: -0.1700
Data Index: 4105100 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.2046. Min Act: -0.1700
Data Index: 8231245 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.2046. Min Act: -0.1700
Data Index: 2458515 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.1733. Min Act: -0.1700
Data Index: 7015494 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.1108. Min Act: -0.1700
Data Index: 7814549 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.1108. Min Act: -0.1700
Data Index: 1812900 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.0796. Min Act: -0.1700
Data Index: 1941000 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.0483. Min Act: -0.1700
Data Index: 2028866 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.0483. Min Act: -0.1700
Data Index: 8335797 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.0170. Min Act: -0.1700
Data Index: 3902072 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.0170. Min Act: -0.1700
Data Index: 6550306 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.0170. Min Act: -0.1700
Data Index: 6098882 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.0170. Min Act: -0.1700
Data Index: 2065796 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.0170. Min Act: -0.1700
Data Index: 21387 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2358. Min Range: -4.2358
Max Act: 4.0170. Min Act: -0.1700
Data Index: 8001702 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2358. Min Range: -4.2358
Max Act: 3.9858. Min Act: -0.1700
Data Index: 5690115 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2358. Min Range: -4.2358
Max Act: 3.9545. Min Act: -0.1700
Data Index: 6227141 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2358. Min Range: -4.2358
Max Act: 3.9233. Min Act: -0.1700
Data Index: 7396689 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2358. Min Range: -4.2358
Max Act: 3.9545. Min Act: -0.1700
Data Index: 2223053 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2358. Min Range: -4.2358
Max Act: 3.9545. Min Act: -0.1700
Data Index: 40657 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19