Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 914 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0006

Data Index: 837786 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0326. Min Act: -0.0006

Data Index: 1135398 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0326. Min Act: -0.0006

Data Index: 776939 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1319316 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0311. Min Act: -0.0006

Data Index: 74861 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0305. Min Act: -0.0006

Data Index: 490838 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0309. Min Act: -0.0006

Data Index: 785375 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0309. Min Act: -0.0006

Data Index: 10225 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0299. Min Act: -0.0006

Data Index: 6719 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0302. Min Act: -0.0006

Data Index: 995865 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0302. Min Act: -0.0006

Data Index: 963452 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0307. Min Act: -0.0006

Data Index: 752090 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0312. Min Act: -0.0006

Data Index: 209940 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0299. Min Act: -0.0006

Data Index: 459540 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0286. Min Act: -0.0006

Data Index: 205366 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0284. Min Act: -0.0006

Data Index: 295154 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0290. Min Act: -0.0006

Data Index: 815868 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1223365 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0279. Min Act: -0.0006

Data Index: 424785 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0278. Min Act: -0.0006

Data Index: 915143 (C4 (Web Text))

Max Activating Token Index: 265