Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2432. Min Range: -7.2432
Max Act: 7.2432. Min Act: -0.1700
Data Index: 4909610 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2432. Min Range: -7.2432
Max Act: 7.1494. Min Act: -0.1700
Data Index: 4875559 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2432. Min Range: -7.2432
Max Act: 7.0244. Min Act: -0.1700
Data Index: 3325071 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.9619. Min Act: -0.1700
Data Index: 681587 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.7432. Min Act: -0.1700
Data Index: 4843840 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.7119. Min Act: -0.1700
Data Index: 7277702 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.7119. Min Act: -0.1700
Data Index: 5705316 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.6807. Min Act: -0.1700
Data Index: 3146582 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.7119. Min Act: -0.1700
Data Index: 5547574 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.5869. Min Act: -0.1700
Data Index: 419170 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.6182. Min Act: -0.1700
Data Index: 3736968 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.6182. Min Act: -0.1700
Data Index: 7347505 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.6182. Min Act: -0.1700
Data Index: 8507267 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.5869. Min Act: -0.1700
Data Index: 7083150 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.5869. Min Act: -0.1700
Data Index: 3824824 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.6182. Min Act: -0.1700
Data Index: 1556096 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.5557. Min Act: -0.1700
Data Index: 3209983 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.5557. Min Act: -0.1700
Data Index: 5811811 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.5869. Min Act: -0.1700
Data Index: 5493641 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2432. Min Range: -7.2432
Max Act: 6.5557. Min Act: -0.1700
Data Index: 1701809 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19