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

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

Neuron 134 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: 3.4756. Min Range: -3.4756

Max Act: 3.4756. Min Act: -0.0000

Data Index: 1224531 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 3.4756. Min Range: -3.4756

Max Act: 3.0793. Min Act: -0.0000

Data Index: 887235 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 3.4756. Min Range: -3.4756

Max Act: 3.1505. Min Act: -0.0000

Data Index: 1297807 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 3.4756. Min Range: -3.4756

Max Act: 3.1353. Min Act: -0.0000

Data Index: 1160119 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 3.4756. Min Range: -3.4756

Max Act: 3.2391. Min Act: -0.0000

Data Index: 335991 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.9433. Min Act: -0.0000

Data Index: 704301 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 3.4756. Min Range: -3.4756

Max Act: 3.0681. Min Act: -0.0000

Data Index: 637524 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.8947. Min Act: -0.0000

Data Index: 953913 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.7416. Min Act: -0.0000

Data Index: 864902 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.8650. Min Act: -0.0000

Data Index: 432657 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 3.4756. Min Range: -3.4756

Max Act: 3.1093. Min Act: -0.0000

Data Index: 422840 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 3.4756. Min Range: -3.4756

Max Act: 3.0166. Min Act: -0.0000

Data Index: 181408 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.7546. Min Act: -0.0000

Data Index: 317461 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.7243. Min Act: -0.0000

Data Index: 647182 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.8709. Min Act: -0.0000

Data Index: 1336479 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.6610. Min Act: -0.0000

Data Index: 8691 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.7335. Min Act: -0.0000

Data Index: 647467 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.4487. Min Act: -0.0000

Data Index: 1431986 (Python Code)

Max Activating Token Index: 591

Text #18

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.2984. Min Act: -0.0000

Data Index: 1020430 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 3.4756. Min Range: -3.4756

Max Act: 2.4519. Min Act: -0.0000

Data Index: 838201 (C4 (Web Text))

Max Activating Token Index: 266