Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5631 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1702. Min Range: -3.1702
Max Act: 3.1702. Min Act: -0.1700
Data Index: 1857667 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.9810. Min Act: -0.1700
Data Index: 6179490 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.9493. Min Act: -0.1700
Data Index: 566449 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.9177. Min Act: -0.1700
Data Index: 8657604 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.9018. Min Act: -0.1700
Data Index: 2158385 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8859. Min Act: -0.1700
Data Index: 3763960 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8859. Min Act: -0.1700
Data Index: 5267505 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8859. Min Act: -0.1700
Data Index: 3846666 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8701. Min Act: -0.1700
Data Index: 7330329 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8542. Min Act: -0.1700
Data Index: 5267690 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8701. Min Act: -0.1700
Data Index: 7205733 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8859. Min Act: -0.1700
Data Index: 4394750 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8383. Min Act: -0.1700
Data Index: 1622492 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8224. Min Act: -0.1700
Data Index: 3844864 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8224. Min Act: -0.1700
Data Index: 3494802 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8224. Min Act: -0.1700
Data Index: 8198676 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8224. Min Act: -0.1700
Data Index: 8442397 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8224. Min Act: -0.1700
Data Index: 2838310 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8224. Min Act: -0.1700
Data Index: 971337 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1702. Min Range: -3.1702
Max Act: 2.8065. Min Act: -0.1700
Data Index: 2839311 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19