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

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

Neuron 3016 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: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1065257 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0285. Min Act: -0.0003

Data Index: 300043 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1133084 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0305. Min Act: -0.0003

Data Index: 540445 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1073510 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0247. Min Act: -0.0003

Data Index: 709695 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0270. Min Act: -0.0003

Data Index: 727259 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1357888 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1082246 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0248. Min Act: -0.0003

Data Index: 399718 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0247. Min Act: -0.0003

Data Index: 512697 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0236. Min Act: -0.0003

Data Index: 862531 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0243. Min Act: -0.0003

Data Index: 881574 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0243. Min Act: -0.0003

Data Index: 957053 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0243. Min Act: -0.0003

Data Index: 4352 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0230. Min Act: -0.0003

Data Index: 544075 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0241. Min Act: -0.0003

Data Index: 420068 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0244. Min Act: -0.0003

Data Index: 788706 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0233. Min Act: -0.0003

Data Index: 248645 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0228. Min Act: -0.0003

Data Index: 510725 (C4 (Web Text))

Max Activating Token Index: 353