Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3933 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0059. Min Range: -3.0059

Max Act: 3.0059. Min Act: -0.0000

Data Index: 750882 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.4482. Min Act: -0.0000

Data Index: 1307972 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.1606. Min Act: -0.0000

Data Index: 543171 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.3670. Min Act: -0.0000

Data Index: 321896 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.2897. Min Act: -0.0000

Data Index: 522810 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.2599. Min Act: -0.0000

Data Index: 368597 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.3377. Min Act: -0.0000

Data Index: 1351968 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.1648. Min Act: -0.0000

Data Index: 1357796 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.1205. Min Act: -0.0000

Data Index: 123549 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 3.0059. Min Range: -3.0059

Max Act: 1.9232. Min Act: -0.0000

Data Index: 337619 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 3.0059. Min Range: -3.0059

Max Act: 1.8983. Min Act: -0.0000

Data Index: 965299 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.0916. Min Act: -0.0000

Data Index: 1007354 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.1911. Min Act: -0.0000

Data Index: 30615 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.0750. Min Act: -0.0000

Data Index: 487276 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.0868. Min Act: -0.0000

Data Index: 269899 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 3.0059. Min Range: -3.0059

Max Act: 1.9718. Min Act: -0.0000

Data Index: 1194635 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.0828. Min Act: -0.0000

Data Index: 6609 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 3.0059. Min Range: -3.0059

Max Act: 1.9574. Min Act: -0.0000

Data Index: 692290 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.0059. Min Range: -3.0059

Max Act: 1.9479. Min Act: -0.0000

Data Index: 889568 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 3.0059. Min Range: -3.0059

Max Act: 1.9306. Min Act: -0.0000

Data Index: 43664 (C4 (Web Text))

Max Activating Token Index: 473