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

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

Neuron 706 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0335. Min Range: -1.0335

Max Act: 1.0335. Min Act: -0.0001

Data Index: 1128809 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.0335. Min Range: -1.0335

Max Act: 1.0328. Min Act: -0.0001

Data Index: 1109209 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.0335. Min Range: -1.0335

Max Act: 1.0150. Min Act: -0.0001

Data Index: 5204 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9819. Min Act: -0.0001

Data Index: 1305191 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9177. Min Act: -0.0001

Data Index: 583041 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9966. Min Act: -0.0001

Data Index: 479518 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9856. Min Act: -0.0001

Data Index: 251891 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9464. Min Act: -0.0001

Data Index: 290759 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9247. Min Act: -0.0001

Data Index: 923141 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9638. Min Act: -0.0001

Data Index: 472606 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9037. Min Act: -0.0001

Data Index: 226246 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8984. Min Act: -0.0001

Data Index: 1358394 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8800. Min Act: -0.0001

Data Index: 636062 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9519. Min Act: -0.0001

Data Index: 89572 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9277. Min Act: -0.0001

Data Index: 584528 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9232. Min Act: -0.0001

Data Index: 881885 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9533. Min Act: -0.0001

Data Index: 1064958 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9236. Min Act: -0.0001

Data Index: 192698 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9176. Min Act: -0.0001

Data Index: 1201829 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8869. Min Act: -0.0001

Data Index: 1097100 (C4 (Web Text))

Max Activating Token Index: 339