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

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

Neuron 2311 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8263. Min Act: -0.0001

Data Index: 404700 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8664. Min Act: -0.0000

Data Index: 723719 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8506. Min Act: -0.0000

Data Index: 297331 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7265. Min Act: -0.0001

Data Index: 94812 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8333. Min Act: -0.0001

Data Index: 890436 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7786. Min Act: -0.0000

Data Index: 823082 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7541. Min Act: -0.0001

Data Index: 201203 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7690. Min Act: -0.0000

Data Index: 792335 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7443. Min Act: -0.0000

Data Index: 22599 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1074287 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6773. Min Act: -0.0001

Data Index: 361944 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7726. Min Act: -0.0001

Data Index: 1239783 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7449. Min Act: -0.0000

Data Index: 690967 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1222801 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7658. Min Act: -0.0001

Data Index: 448031 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8297. Min Act: -0.0001

Data Index: 461826 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7134. Min Act: -0.0001

Data Index: 808136 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7334. Min Act: -0.0000

Data Index: 472484 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1219576 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7131. Min Act: -0.0000

Data Index: 493343 (C4 (Web Text))

Max Activating Token Index: 405