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

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

Neuron 1412 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1066304 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4618. Min Act: -0.0000

Data Index: 824456 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4300. Min Act: -0.0000

Data Index: 142594 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4304. Min Act: -0.0000

Data Index: 657588 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4114. Min Act: 0.0000

Data Index: 1296654 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3837. Min Act: -0.0000

Data Index: 938310 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3768. Min Act: -0.0000

Data Index: 583299 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3739. Min Act: -0.0000

Data Index: 31671 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1265977 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3878. Min Act: -0.0000

Data Index: 500579 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1107591 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3654. Min Act: -0.0000

Data Index: 26552 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1327004 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3503. Min Act: -0.0000

Data Index: 691890 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3517. Min Act: -0.0000

Data Index: 427877 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1198757 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1121120 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3119. Min Act: -0.0000

Data Index: 439531 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1177458 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1488227 (Python Code)

Max Activating Token Index: 603