Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3304 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0231. Min Range: -2.0231

Max Act: 2.0231. Min Act: -0.0000

Data Index: 1123505 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.7377. Min Act: -0.0000

Data Index: 349284 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1040020 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.6040. Min Act: -0.0000

Data Index: 414633 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.6640. Min Act: -0.0000

Data Index: 164737 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.4146. Min Act: -0.0000

Data Index: 1208020 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.5054. Min Act: -0.0000

Data Index: 1241236 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.4693. Min Act: -0.0001

Data Index: 826312 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.6468. Min Act: -0.0000

Data Index: 235828 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.1338. Min Act: -0.0000

Data Index: 104028 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.4380. Min Act: -0.0001

Data Index: 282878 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1003330 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.4951. Min Act: -0.0000

Data Index: 233181 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.2835. Min Act: -0.0000

Data Index: 914558 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.3093. Min Act: -0.0001

Data Index: 449845 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.2316. Min Act: -0.0000

Data Index: 964526 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.2854. Min Act: -0.0000

Data Index: 134994 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1070010 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.1961. Min Act: -0.0001

Data Index: 1106297 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 2.0231. Min Range: -2.0231

Max Act: 1.2966. Min Act: -0.0000

Data Index: 986917 (C4 (Web Text))

Max Activating Token Index: 257