Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4972 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.3864. Min Act: -0.1700
Data Index: 3437211 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.3708. Min Act: -0.1700
Data Index: 1250757 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.3237. Min Act: -0.1700
Data Index: 658720 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.2923. Min Act: -0.1700
Data Index: 3957528 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.2452. Min Act: -0.1700
Data Index: 2723455 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.2137. Min Act: -0.1700
Data Index: 4120721 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.2137. Min Act: -0.1700
Data Index: 6026317 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1980. Min Act: -0.1700
Data Index: 5404478 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1823. Min Act: -0.1700
Data Index: 5931050 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1823. Min Act: -0.1700
Data Index: 8749109 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1823. Min Act: -0.1700
Data Index: 7824145 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1823. Min Act: -0.1700
Data Index: 7390781 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1823. Min Act: -0.1700
Data Index: 7484591 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1508. Min Act: -0.1700
Data Index: 4042063 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1508. Min Act: -0.1700
Data Index: 584086 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1508. Min Act: -0.1700
Data Index: 3133516 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1351. Min Act: -0.1700
Data Index: 5627086 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1193. Min Act: -0.1700
Data Index: 4613675 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1193. Min Act: -0.1700
Data Index: 6164413 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1193. Min Act: -0.1700
Data Index: 7190606 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19