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

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

Neuron 4014 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: 0.0437. Min Range: -0.0437

Max Act: 0.0428. Min Act: -0.0003

Data Index: 934537 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1195141 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0379. Min Act: -0.0003

Data Index: 982606 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0403. Min Act: -0.0003

Data Index: 18140 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0407. Min Act: -0.0003

Data Index: 56916 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0398. Min Act: -0.0003

Data Index: 301825 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0389. Min Act: -0.0003

Data Index: 417515 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0408. Min Act: -0.0003

Data Index: 385004 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0401. Min Act: -0.0003

Data Index: 47335 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1217539 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0421. Min Act: -0.0003

Data Index: 126638 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1649522 (Python Code)

Max Activating Token Index: 322

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0397. Min Act: -0.0003

Data Index: 667054 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0418. Min Act: -0.0003

Data Index: 226152 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0390. Min Act: -0.0003

Data Index: 163752 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0373. Min Act: -0.0003

Data Index: 899149 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0402. Min Act: -0.0003

Data Index: 21826 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0385. Min Act: -0.0003

Data Index: 521397 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1044181 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1361814 (Python Code)

Max Activating Token Index: 9