Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3010 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1052. Min Range: -3.1052

Max Act: 3.1052. Min Act: -0.0000

Data Index: 1082017 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.5332. Min Act: -0.0000

Data Index: 822884 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.2781. Min Act: -0.0000

Data Index: 703601 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.4169. Min Act: -0.0000

Data Index: 1021016 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 3.1052. Min Range: -3.1052

Max Act: 1.9013. Min Act: -0.0000

Data Index: 1084245 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.0795. Min Act: -0.0000

Data Index: 1128187 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.3100. Min Act: -0.0000

Data Index: 1314319 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.1817. Min Act: -0.0000

Data Index: 674789 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 3.1052. Min Range: -3.1052

Max Act: 1.9757. Min Act: -0.0000

Data Index: 822951 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.0477. Min Act: -0.0000

Data Index: 990824 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.0373. Min Act: -0.0000

Data Index: 391927 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.0010. Min Act: -0.0000

Data Index: 51628 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 3.1052. Min Range: -3.1052

Max Act: 1.9910. Min Act: -0.0000

Data Index: 982506 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 3.1052. Min Range: -3.1052

Max Act: 1.8912. Min Act: -0.0000

Data Index: 708164 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.0738. Min Act: -0.0000

Data Index: 653220 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.0313. Min Act: -0.0000

Data Index: 856331 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 3.1052. Min Range: -3.1052

Max Act: 2.0392. Min Act: -0.0000

Data Index: 1006383 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 3.1052. Min Range: -3.1052

Max Act: 1.7209. Min Act: -0.0000

Data Index: 170628 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 3.1052. Min Range: -3.1052

Max Act: 1.9189. Min Act: -0.0000

Data Index: 498682 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 3.1052. Min Range: -3.1052

Max Act: 1.9777. Min Act: -0.0000

Data Index: 571044 (C4 (Web Text))

Max Activating Token Index: 982