Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 308 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4480. Min Act: -0.0003

Data Index: 825304 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4429. Min Act: -0.0003

Data Index: 133604 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4424. Min Act: -0.0003

Data Index: 963386 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4191. Min Act: -0.0003

Data Index: 511253 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4283. Min Act: -0.0003

Data Index: 158823 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4279. Min Act: -0.0003

Data Index: 1258792 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4234. Min Act: -0.0003

Data Index: 675082 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4187. Min Act: -0.0003

Data Index: 71928 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3954. Min Act: -0.0003

Data Index: 663047 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3992. Min Act: -0.0003

Data Index: 1114257 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4269. Min Act: -0.0003

Data Index: 324969 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4100. Min Act: -0.0003

Data Index: 1313042 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4089. Min Act: -0.0003

Data Index: 54119 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3658. Min Act: -0.0003

Data Index: 927727 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4071. Min Act: -0.0003

Data Index: 1086659 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3885. Min Act: -0.0003

Data Index: 220893 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3748. Min Act: -0.0003

Data Index: 1300041 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3616. Min Act: -0.0003

Data Index: 1304746 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4052. Min Act: -0.0003

Data Index: 372710 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4158. Min Act: -0.0003

Data Index: 355613 (C4 (Web Text))

Max Activating Token Index: 685