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

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

Neuron 84 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: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0003

Data Index: 113814 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0408. Min Act: -0.0003

Data Index: 389146 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1307021 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0464. Min Act: -0.0003

Data Index: 303819 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0435. Min Act: -0.0003

Data Index: 773814 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1276194 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0440. Min Act: -0.0003

Data Index: 752203 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0469. Min Act: -0.0003

Data Index: 831319 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1335381 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0462. Min Act: -0.0003

Data Index: 271997 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0457. Min Act: -0.0003

Data Index: 100616 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0387. Min Act: -0.0003

Data Index: 793534 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0382. Min Act: -0.0004

Data Index: 760411 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1030170 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0413. Min Act: -0.0004

Data Index: 1005260 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0366. Min Act: -0.0003

Data Index: 527694 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0412. Min Act: -0.0003

Data Index: 714638 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0464. Min Act: -0.0003

Data Index: 385337 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1357734 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0361. Min Act: -0.0003

Data Index: 443102 (C4 (Web Text))

Max Activating Token Index: 81