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

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

Neuron 1728 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8244. Min Act: -0.0001

Data Index: 635906 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8188. Min Act: -0.0001

Data Index: 731975 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7891. Min Act: -0.0001

Data Index: 351527 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7576. Min Act: -0.0001

Data Index: 483489 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8461. Min Act: -0.0001

Data Index: 1163845 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7908. Min Act: -0.0001

Data Index: 451362 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7660. Min Act: -0.0001

Data Index: 1061083 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6978. Min Act: -0.0001

Data Index: 736096 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7469. Min Act: -0.0001

Data Index: 173074 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7601. Min Act: -0.0001

Data Index: 682514 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7393. Min Act: -0.0001

Data Index: 1181786 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6942. Min Act: -0.0001

Data Index: 251641 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7367. Min Act: -0.0001

Data Index: 1329766 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7248. Min Act: -0.0001

Data Index: 725644 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7486. Min Act: -0.0001

Data Index: 12099 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7473. Min Act: -0.0001

Data Index: 432747 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7410. Min Act: -0.0001

Data Index: 704669 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1049914 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7386. Min Act: -0.0001

Data Index: 62872 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7067. Min Act: -0.0001

Data Index: 384140 (C4 (Web Text))

Max Activating Token Index: 95