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

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

Neuron 3221 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6798. Min Act: -0.0000

Data Index: 342940 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 5.0167. Min Range: -5.0167

Max Act: 5.0167. Min Act: -0.0000

Data Index: 624504 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5460. Min Act: -0.0000

Data Index: 1150339 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6859. Min Act: -0.0000

Data Index: 1318056 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6851. Min Act: -0.0000

Data Index: 587773 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.4967. Min Act: -0.0000

Data Index: 1220192 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.8512. Min Act: -0.0000

Data Index: 34756 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.4990. Min Act: -0.0000

Data Index: 952647 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6412. Min Act: -0.0000

Data Index: 1027125 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6204. Min Act: -0.0000

Data Index: 126768 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.9080. Min Act: -0.0000

Data Index: 598679 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.3380. Min Act: -0.0000

Data Index: 670397 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.1456. Min Act: -0.0000

Data Index: 265827 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.8395. Min Act: -0.0000

Data Index: 1174139 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.4996. Min Act: -0.0000

Data Index: 1283252 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.4966. Min Act: -0.0000

Data Index: 583862 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.8405. Min Act: -0.0000

Data Index: 838016 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5054. Min Act: -0.0000

Data Index: 1152464 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6723. Min Act: -0.0000

Data Index: 792957 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.4652. Min Act: -0.0000

Data Index: 1238643 (C4 (Web Text))

Max Activating Token Index: 703