Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 101 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0006

Data Index: 101324 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0427. Min Act: -0.0006

Data Index: 492355 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0399. Min Act: -0.0006

Data Index: 546770 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0394. Min Act: -0.0006

Data Index: 1271469 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0386. Min Act: -0.0006

Data Index: 912823 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0383. Min Act: -0.0006

Data Index: 229838 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0395. Min Act: -0.0006

Data Index: 811856 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0388. Min Act: -0.0006

Data Index: 1252949 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0377. Min Act: -0.0006

Data Index: 191464 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0362. Min Act: -0.0006

Data Index: 530542 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1153834 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0365. Min Act: -0.0006

Data Index: 947714 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0387. Min Act: -0.0006

Data Index: 1190190 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0394. Min Act: -0.0006

Data Index: 116383 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0379. Min Act: -0.0006

Data Index: 136171 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1333899 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0389. Min Act: -0.0006

Data Index: 882276 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0381. Min Act: -0.0006

Data Index: 85132 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0373. Min Act: -0.0006

Data Index: 849952 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1012550 (C4 (Web Text))

Max Activating Token Index: 868