Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2384. Min Range: -4.2384
Max Act: 4.2384. Min Act: -0.1700
Data Index: 7663497 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2384. Min Range: -4.2384
Max Act: 4.2071. Min Act: -0.1700
Data Index: 3072136 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.9571. Min Act: -0.1700
Data Index: 4373768 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.9571. Min Act: -0.1700
Data Index: 6190599 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8945. Min Act: -0.1700
Data Index: 1223865 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8945. Min Act: -0.1700
Data Index: 3213797 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8633. Min Act: -0.1700
Data Index: 2997571 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8945. Min Act: -0.1700
Data Index: 2402763 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8945. Min Act: -0.1700
Data Index: 2601192 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8945. Min Act: -0.1700
Data Index: 5327281 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8945. Min Act: -0.1700
Data Index: 3451254 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8945. Min Act: -0.1700
Data Index: 6594116 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8633. Min Act: -0.1700
Data Index: 5202026 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8320. Min Act: -0.1700
Data Index: 5833775 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8320. Min Act: -0.1700
Data Index: 8100378 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8633. Min Act: -0.1700
Data Index: 5306605 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8320. Min Act: -0.1700
Data Index: 4618538 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8007. Min Act: -0.1700
Data Index: 4879794 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.7694. Min Act: -0.1700
Data Index: 6213481 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2384. Min Range: -4.2384
Max Act: 3.8007. Min Act: -0.1700
Data Index: 3973731 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19