Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2485. Min Range: -6.2485
Max Act: 6.2485. Min Act: -0.1700
Data Index: 5120026 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.9985. Min Act: -0.1700
Data Index: 5607775 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.9048. Min Act: -0.1700
Data Index: 7414177 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.8110. Min Act: -0.1700
Data Index: 5259211 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.8110. Min Act: -0.1700
Data Index: 4778156 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.7798. Min Act: -0.1700
Data Index: 2033671 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.8110. Min Act: -0.1700
Data Index: 7203164 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.7485. Min Act: -0.1700
Data Index: 887117 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.7485. Min Act: -0.1700
Data Index: 4399537 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.7173. Min Act: -0.1700
Data Index: 6276412 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.7173. Min Act: -0.1700
Data Index: 1397884 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.7173. Min Act: -0.1700
Data Index: 7936513 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.7173. Min Act: -0.1700
Data Index: 2346816 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.6860. Min Act: -0.1700
Data Index: 4243814 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.6860. Min Act: -0.1700
Data Index: 6601448 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.6548. Min Act: -0.1700
Data Index: 4058360 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.6235. Min Act: -0.1700
Data Index: 3872091 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.6548. Min Act: -0.1700
Data Index: 2104577 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.6548. Min Act: -0.1700
Data Index: 7268867 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2485. Min Range: -6.2485
Max Act: 5.6235. Min Act: -0.1700
Data Index: 2412662 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19