Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2480 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.5186. Min Act: -0.0001

Data Index: 69085 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1154378 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4951. Min Act: -0.0001

Data Index: 546710 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4400. Min Act: -0.0001

Data Index: 1008641 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4983. Min Act: -0.0001

Data Index: 1210176 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4795. Min Act: -0.0001

Data Index: 1190341 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4781. Min Act: -0.0001

Data Index: 1074041 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4211. Min Act: -0.0001

Data Index: 532608 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4330. Min Act: -0.0001

Data Index: 985238 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4215. Min Act: -0.0001

Data Index: 196193 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4279. Min Act: -0.0001

Data Index: 293920 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4302. Min Act: -0.0001

Data Index: 627143 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4104. Min Act: -0.0001

Data Index: 164473 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.3955. Min Act: -0.0000

Data Index: 479873 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.3921. Min Act: -0.0001

Data Index: 779862 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4199. Min Act: -0.0001

Data Index: 1014705 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4183. Min Act: -0.0001

Data Index: 119645 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4174. Min Act: -0.0001

Data Index: 1188929 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4293. Min Act: -0.0001

Data Index: 221594 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4283. Min Act: -0.0000

Data Index: 693445 (C4 (Web Text))

Max Activating Token Index: 933