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

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

Neuron 226 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.1106. Min Act: -0.0002

Data Index: 1124182 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.1003. Min Act: -0.0002

Data Index: 323690 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.0899. Min Act: -0.0002

Data Index: 384996 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.0700. Min Act: -0.0002

Data Index: 945319 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.0495. Min Act: -0.0002

Data Index: 708460 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.0183. Min Act: -0.0002

Data Index: 1100190 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9911. Min Act: -0.0002

Data Index: 540748 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9754. Min Act: -0.0002

Data Index: 154581 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9590. Min Act: -0.0002

Data Index: 635169 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9533. Min Act: -0.0002

Data Index: 1223584 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9501. Min Act: -0.0002

Data Index: 319715 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9555. Min Act: -0.0002

Data Index: 535897 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9539. Min Act: -0.0002

Data Index: 205844 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9479. Min Act: -0.0002

Data Index: 652778 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9315. Min Act: -0.0002

Data Index: 926300 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9228. Min Act: -0.0002

Data Index: 1154372 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9272. Min Act: -0.0002

Data Index: 1117668 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9147. Min Act: -0.0002

Data Index: 189290 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9238. Min Act: -0.0002

Data Index: 292515 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8968. Min Act: -0.0002

Data Index: 484733 (C4 (Web Text))

Max Activating Token Index: 333