Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 417 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0003

Data Index: 357715 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1206287 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1352090 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0432. Min Act: -0.0003

Data Index: 706860 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0442. Min Act: -0.0003

Data Index: 311834 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1319157 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0450. Min Act: -0.0003

Data Index: 777970 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1237407 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0447. Min Act: -0.0003

Data Index: 710541 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0439. Min Act: -0.0003

Data Index: 796432 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1169244 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0432. Min Act: -0.0003

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0415. Min Act: -0.0003

Data Index: 665721 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0416. Min Act: -0.0003

Data Index: 129779 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1291200 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0414. Min Act: -0.0003

Data Index: 584562 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0423. Min Act: -0.0003

Data Index: 675402 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0405. Min Act: -0.0003

Data Index: 853541 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0440. Min Act: -0.0003

Data Index: 601626 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1289457 (C4 (Web Text))

Max Activating Token Index: 311