Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2764 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4672. Min Range: -8.4672
Max Act: 8.4672. Min Act: -0.1700
Data Index: 1454518 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.9672. Min Act: -0.1700
Data Index: 8297041 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.9047. Min Act: -0.1700
Data Index: 3331012 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.9047. Min Act: -0.1700
Data Index: 4164624 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.9047. Min Act: -0.1700
Data Index: 6870653 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.8109. Min Act: -0.1700
Data Index: 6657179 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.7797. Min Act: -0.1700
Data Index: 5067371 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.7797. Min Act: -0.1700
Data Index: 1880573 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.7172. Min Act: -0.1700
Data Index: 2600122 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.7172. Min Act: -0.1700
Data Index: 1455694 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.6859. Min Act: -0.1700
Data Index: 3075287 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.5922. Min Act: -0.1700
Data Index: 1410461 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.6234. Min Act: -0.1700
Data Index: 2554695 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.5609. Min Act: -0.1700
Data Index: 1962596 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.5609. Min Act: -0.1700
Data Index: 2464220 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.5609. Min Act: -0.1700
Data Index: 7291962 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.4984. Min Act: -0.1700
Data Index: 6179786 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.5297. Min Act: -0.1700
Data Index: 6544750 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.5297. Min Act: -0.1700
Data Index: 6747508 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4672. Min Range: -8.4672
Max Act: 7.5297. Min Act: -0.1700
Data Index: 3371731 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19