Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.9610. Min Act: -0.1700
Data Index: 5642174 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.8047. Min Act: -0.1700
Data Index: 5228927 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.5860. Min Act: -0.1700
Data Index: 6635657 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.5547. Min Act: -0.1700
Data Index: 4062862 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.5547. Min Act: -0.1700
Data Index: 3134861 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.4610. Min Act: -0.1700
Data Index: 7611474 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.4297. Min Act: -0.1700
Data Index: 607665 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.4297. Min Act: -0.1700
Data Index: 8529359 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.4297. Min Act: -0.1700
Data Index: 6281023 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.3985. Min Act: -0.1700
Data Index: 114987 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.3985. Min Act: -0.1700
Data Index: 429580 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.3985. Min Act: -0.1700
Data Index: 765611 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.3672. Min Act: -0.1700
Data Index: 4882984 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.3047. Min Act: -0.1700
Data Index: 1183086 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.2735. Min Act: -0.1700
Data Index: 6916677 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.2735. Min Act: -0.1700
Data Index: 8478220 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.2735. Min Act: -0.1700
Data Index: 2559618 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.2735. Min Act: -0.1700
Data Index: 5768662 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.2735. Min Act: -0.1700
Data Index: 4455366 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9610. Min Range: -6.9610
Max Act: 6.2735. Min Act: -0.1700
Data Index: 6001931 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19