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

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

Neuron 128 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: 2.4185. Min Range: -2.4185

Max Act: 2.4185. Min Act: -0.0000

Data Index: 583581 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 2.4185. Min Range: -2.4185

Max Act: 2.0657. Min Act: -0.0000

Data Index: 537301 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.9988. Min Act: -0.0000

Data Index: 148672 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.9744. Min Act: -0.0001

Data Index: 821758 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.8238. Min Act: -0.0000

Data Index: 117227 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.9623. Min Act: -0.0000

Data Index: 299167 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.8818. Min Act: -0.0001

Data Index: 1323496 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.8730. Min Act: -0.0000

Data Index: 884269 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.6890. Min Act: -0.0000

Data Index: 1302511 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.8287. Min Act: -0.0000

Data Index: 1357154 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.8899. Min Act: -0.0001

Data Index: 1176869 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.8562. Min Act: -0.0001

Data Index: 1027821 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.9978. Min Act: -0.0000

Data Index: 1185473 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.7890. Min Act: -0.0000

Data Index: 1217848 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.7002. Min Act: -0.0000

Data Index: 226289 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.7117. Min Act: -0.0000

Data Index: 645247 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.6681. Min Act: -0.0000

Data Index: 761773 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.6538. Min Act: -0.0001

Data Index: 875532 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.5461. Min Act: -0.0001

Data Index: 968042 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 2.4185. Min Range: -2.4185

Max Act: 1.6778. Min Act: -0.0001

Data Index: 885396 (C4 (Web Text))

Max Activating Token Index: 816