Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1789 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1367965 (Python Code)

Max Activating Token Index: 929

Text #1

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0317. Min Act: -0.0005

Data Index: 158973 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0323. Min Act: -0.0005

Data Index: 907957 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0334. Min Act: -0.0005

Data Index: 403268 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0309. Min Act: -0.0005

Data Index: 111727 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0301. Min Act: -0.0005

Data Index: 758189 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0338. Min Act: -0.0005

Data Index: 489695 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0303. Min Act: -0.0005

Data Index: 94115 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0320. Min Act: -0.0005

Data Index: 810773 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0318. Min Act: -0.0005

Data Index: 813646 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0305. Min Act: -0.0005

Data Index: 1217688 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0306. Min Act: -0.0005

Data Index: 312988 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0291. Min Act: -0.0005

Data Index: 898200 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0317. Min Act: -0.0005

Data Index: 579332 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0282. Min Act: -0.0005

Data Index: 985434 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0301. Min Act: -0.0005

Data Index: 678791 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0300. Min Act: -0.0005

Data Index: 843814 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0283. Min Act: -0.0005

Data Index: 319515 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0317. Min Act: -0.0005

Data Index: 798012 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0297. Min Act: -0.0005

Data Index: 104377 (C4 (Web Text))

Max Activating Token Index: 844