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

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

Neuron 6052 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.7214. Min Act: -0.0001

Data Index: 275257 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.6373. Min Act: -0.0001

Data Index: 111230 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2454. Min Act: -0.0001

Data Index: 315555 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.5904. Min Act: -0.0001

Data Index: 269049 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.6646. Min Act: -0.0001

Data Index: 966937 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.5450. Min Act: -0.0001

Data Index: 409187 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.5907. Min Act: -0.0001

Data Index: 627798 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4879. Min Act: -0.0001

Data Index: 1064571 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.5349. Min Act: -0.0001

Data Index: 543944 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4205. Min Act: -0.0001

Data Index: 588560 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2581. Min Act: -0.0001

Data Index: 292559 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4931. Min Act: -0.0001

Data Index: 693137 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2654. Min Act: -0.0001

Data Index: 1273249 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.1867. Min Act: -0.0001

Data Index: 141371 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.3289. Min Act: -0.0001

Data Index: 1303128 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2025. Min Act: -0.0001

Data Index: 60523 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2280. Min Act: -0.0001

Data Index: 501778 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2771. Min Act: -0.0001

Data Index: 951492 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2418. Min Act: -0.0001

Data Index: 421448 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.3484. Min Act: -0.0001

Data Index: 1208259 (C4 (Web Text))

Max Activating Token Index: 984