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

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

Neuron 662 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0541. Min Act: -0.0006

Data Index: 483301 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1121478 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0467. Min Act: -0.0006

Data Index: 205893 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0474. Min Act: -0.0006

Data Index: 1311222 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0445. Min Act: -0.0006

Data Index: 156416 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0443. Min Act: -0.0006

Data Index: 102435 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0440. Min Act: -0.0006

Data Index: 1184459 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1085508 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0451. Min Act: -0.0006

Data Index: 572036 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0460. Min Act: -0.0006

Data Index: 704723 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0427. Min Act: -0.0006

Data Index: 1253439 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0467. Min Act: -0.0006

Data Index: 798309 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0454. Min Act: -0.0006

Data Index: 774351 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0452. Min Act: -0.0006

Data Index: 1270625 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0442. Min Act: -0.0006

Data Index: 19242 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0423. Min Act: -0.0006

Data Index: 948866 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0419. Min Act: -0.0006

Data Index: 484157 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0427. Min Act: -0.0006

Data Index: 593674 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0424. Min Act: -0.0006

Data Index: 145756 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0414. Min Act: -0.0006

Data Index: 146016 (C4 (Web Text))

Max Activating Token Index: 920