Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1124 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0486. Min Range: -4.0486
Max Act: 4.0486. Min Act: -0.1700
Data Index: 6468017 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.9548. Min Act: -0.1700
Data Index: 6057144 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.8923. Min Act: -0.1700
Data Index: 1600348 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.8923. Min Act: -0.1700
Data Index: 3600206 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.8610. Min Act: -0.1700
Data Index: 2310270 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.8298. Min Act: -0.1700
Data Index: 8623704 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.7985. Min Act: -0.1700
Data Index: 1339586 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.7829. Min Act: -0.1700
Data Index: 3209565 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.7672. Min Act: -0.1700
Data Index: 5331438 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.7672. Min Act: -0.1700
Data Index: 1264999 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.7516. Min Act: -0.1700
Data Index: 5659463 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.7203. Min Act: -0.1700
Data Index: 7903766 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.6890. Min Act: -0.1700
Data Index: 8248513 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.7203. Min Act: -0.1700
Data Index: 3788615 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.6734. Min Act: -0.1700
Data Index: 7960677 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.6890. Min Act: -0.1700
Data Index: 3140653 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.6734. Min Act: -0.1700
Data Index: 1886533 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.6577. Min Act: -0.1700
Data Index: 2093628 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.6577. Min Act: -0.1700
Data Index: 7950466 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0486. Min Range: -4.0486
Max Act: 3.6577. Min Act: -0.1700
Data Index: 1403941 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19