Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 614 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.9447. Min Act: -0.1700
Data Index: 3164686 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.9289. Min Act: -0.1700
Data Index: 345669 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.9289. Min Act: -0.1700
Data Index: 663420 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8972. Min Act: -0.1700
Data Index: 6060789 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8972. Min Act: -0.1700
Data Index: 4710509 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.9131. Min Act: -0.1700
Data Index: 8125806 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8655. Min Act: -0.1700
Data Index: 1648191 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 6515616 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8813. Min Act: -0.1700
Data Index: 1702053 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 8652040 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 2424773 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 5870487 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 5049859 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 6809945 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 4323529 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8496. Min Act: -0.1700
Data Index: 4143557 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8337. Min Act: -0.1700
Data Index: 3160059 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8337. Min Act: -0.1700
Data Index: 2843649 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8019. Min Act: -0.1700
Data Index: 200872 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9447. Min Range: -2.9447
Max Act: 2.8178. Min Act: -0.1700
Data Index: 631361 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19