Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2465 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0003

Data Index: 599612 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0564. Min Act: -0.0003

Data Index: 96825 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0523. Min Act: -0.0003

Data Index: 326281 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0519. Min Act: -0.0003

Data Index: 568940 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0520. Min Act: -0.0003

Data Index: 904386 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1316199 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0514. Min Act: -0.0003

Data Index: 35883 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0489. Min Act: -0.0003

Data Index: 842931 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0495. Min Act: -0.0003

Data Index: 899354 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0492. Min Act: -0.0003

Data Index: 527481 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1177724 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0469. Min Act: -0.0003

Data Index: 96289 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0467. Min Act: -0.0003

Data Index: 574280 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0480. Min Act: -0.0003

Data Index: 981143 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1164610 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1113515 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0445. Min Act: -0.0003

Data Index: 852518 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0389. Min Act: -0.0003

Data Index: 805964 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0441. Min Act: -0.0003

Data Index: 882231 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1321134 (C4 (Web Text))

Max Activating Token Index: 27