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

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

Neuron 3050 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: 0.5151. Min Range: -0.5151

Max Act: 0.4968. Min Act: -0.0000

Data Index: 406731 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.4951. Min Act: -0.0000

Data Index: 914061 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1057433 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1281482 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.4255. Min Act: -0.0000

Data Index: 151752 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.4332. Min Act: -0.0000

Data Index: 703697 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3690. Min Act: -0.0000

Data Index: 44279 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3609. Min Act: -0.0000

Data Index: 891553 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3784. Min Act: -0.0000

Data Index: 293010 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1359349 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3537. Min Act: 0.0001

Data Index: 1515594 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3652. Min Act: -0.0000

Data Index: 857599 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3136. Min Act: -0.0000

Data Index: 552548 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3315. Min Act: -0.0000

Data Index: 252315 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3237. Min Act: -0.0000

Data Index: 921799 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3071. Min Act: -0.0000

Data Index: 122274 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3475. Min Act: -0.0000

Data Index: 493785 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3144. Min Act: -0.0000

Data Index: 103369 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1450019 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 0.5151. Min Range: -0.5151

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1585220 (Python Code)

Max Activating Token Index: 836