Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1080 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0003

Data Index: 280020 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0462. Min Act: -0.0003

Data Index: 352447 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0455. Min Act: -0.0003

Data Index: 408350 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0442. Min Act: -0.0003

Data Index: 770172 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0445. Min Act: -0.0003

Data Index: 885535 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0424. Min Act: -0.0003

Data Index: 100720 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0433. Min Act: -0.0003

Data Index: 949572 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0430. Min Act: -0.0003

Data Index: 393861 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1139190 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1225552 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0406. Min Act: -0.0003

Data Index: 994791 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0414. Min Act: -0.0003

Data Index: 246752 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0425. Min Act: -0.0003

Data Index: 530902 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1324955 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0404. Min Act: -0.0003

Data Index: 652282 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0406. Min Act: -0.0003

Data Index: 658154 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0378. Min Act: -0.0003

Data Index: 809512 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0378. Min Act: -0.0003

Data Index: 275422 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0369. Min Act: -0.0003

Data Index: 514710 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1407158 (Python Code)

Max Activating Token Index: 497