Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1785. Min Range: -6.1785
Max Act: 6.1785. Min Act: -0.1700
Data Index: 637138 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1785. Min Range: -6.1785
Max Act: 6.0535. Min Act: -0.1700
Data Index: 599009 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.9910. Min Act: -0.1700
Data Index: 5867675 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.9285. Min Act: -0.1700
Data Index: 1562364 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.9285. Min Act: -0.1700
Data Index: 1560351 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.9285. Min Act: -0.1700
Data Index: 3499593 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.8973. Min Act: -0.1700
Data Index: 1647818 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.9285. Min Act: -0.1700
Data Index: 3131736 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.9285. Min Act: -0.1700
Data Index: 3132631 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.8348. Min Act: -0.1700
Data Index: 6747237 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.8348. Min Act: -0.1700
Data Index: 6201506 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.8035. Min Act: -0.1700
Data Index: 6234271 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.8035. Min Act: -0.1700
Data Index: 569946 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.8035. Min Act: -0.1700
Data Index: 6201508 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.8035. Min Act: -0.1700
Data Index: 5343234 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.7723. Min Act: -0.1700
Data Index: 653104 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.7723. Min Act: -0.1700
Data Index: 8379498 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.7723. Min Act: -0.1700
Data Index: 5938253 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.7723. Min Act: -0.1700
Data Index: 4228625 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1785. Min Range: -6.1785
Max Act: 5.7410. Min Act: -0.1700
Data Index: 3293278 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19