Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.6350. Min Act: -0.1700
Data Index: 4236929 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.2287. Min Act: -0.1700
Data Index: 7668873 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.2600. Min Act: -0.1700
Data Index: 4206839 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.1975. Min Act: -0.1700
Data Index: 8475971 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.1662. Min Act: -0.1700
Data Index: 8245840 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.1662. Min Act: -0.1700
Data Index: 8177801 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.1350. Min Act: -0.1700
Data Index: 5797476 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.1350. Min Act: -0.1700
Data Index: 4655427 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.1350. Min Act: -0.1700
Data Index: 635848 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.0725. Min Act: -0.1700
Data Index: 4206831 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.0412. Min Act: -0.1700
Data Index: 6156173 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.0412. Min Act: -0.1700
Data Index: 5729879 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.0100. Min Act: -0.1700
Data Index: 1688561 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.0412. Min Act: -0.1700
Data Index: 3771239 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6350. Min Range: -5.6350
Max Act: 5.0100. Min Act: -0.1700
Data Index: 7418945 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6350. Min Range: -5.6350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 808487 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6350. Min Range: -5.6350
Max Act: 4.9787. Min Act: -0.1700
Data Index: 7762026 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6350. Min Range: -5.6350
Max Act: 4.9475. Min Act: -0.1700
Data Index: 1742353 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6350. Min Range: -5.6350
Max Act: 4.9475. Min Act: -0.1700
Data Index: 647188 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6350. Min Range: -5.6350
Max Act: 4.9475. Min Act: -0.1700
Data Index: 849491 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19