Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 225 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1171102 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8263. Min Act: -0.0000

Data Index: 405984 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8222. Min Act: -0.0000

Data Index: 521397 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8255. Min Act: -0.0000

Data Index: 878662 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1260181 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8446. Min Act: -0.0000

Data Index: 79259 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8134. Min Act: -0.0000

Data Index: 654833 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1156501 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7444. Min Act: -0.0000

Data Index: 507702 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8228. Min Act: -0.0000

Data Index: 982606 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.6965. Min Act: -0.0000

Data Index: 150816 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7424. Min Act: -0.0000

Data Index: 381946 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7280. Min Act: -0.0000

Data Index: 90199 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.6622. Min Act: -0.0000

Data Index: 664836 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7570. Min Act: -0.0000

Data Index: 180939 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1042478 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1013467 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.6832. Min Act: -0.0000

Data Index: 524301 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.6998. Min Act: -0.0000

Data Index: 909433 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.6944. Min Act: -0.0000

Data Index: 550230 (C4 (Web Text))

Max Activating Token Index: 929