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

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

Neuron 1286 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1137565 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0469. Min Act: -0.0002

Data Index: 152872 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0451. Min Act: -0.0002

Data Index: 199122 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0463. Min Act: -0.0002

Data Index: 774169 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1193082 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0444. Min Act: -0.0002

Data Index: 564845 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0446. Min Act: -0.0002

Data Index: 433839 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0447. Min Act: -0.0002

Data Index: 682767 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1191793 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0443. Min Act: -0.0002

Data Index: 434571 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0424. Min Act: -0.0002

Data Index: 597193 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1260297 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1072688 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0434. Min Act: -0.0003

Data Index: 225337 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1173697 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0415. Min Act: -0.0001

Data Index: 240943 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0420. Min Act: -0.0003

Data Index: 949600 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0413. Min Act: -0.0003

Data Index: 998476 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0418. Min Act: -0.0003

Data Index: 546623 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1240018 (C4 (Web Text))

Max Activating Token Index: 450