Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2312 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1121777 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1102. Min Act: -0.0001

Data Index: 502243 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0920. Min Act: -0.0001

Data Index: 89419 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1218435 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1080. Min Act: -0.0001

Data Index: 538378 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1038. Min Act: -0.0001

Data Index: 288684 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1318172 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1016. Min Act: -0.0001

Data Index: 271376 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1076. Min Act: -0.0001

Data Index: 974595 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1029570 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1008. Min Act: -0.0001

Data Index: 610716 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0883. Min Act: -0.0001

Data Index: 941267 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1310934 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0809. Min Act: -0.0001

Data Index: 266520 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0992. Min Act: -0.0001

Data Index: 538294 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0915. Min Act: -0.0001

Data Index: 234345 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1158189 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0760. Min Act: -0.0001

Data Index: 933911 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0834. Min Act: -0.0001

Data Index: 836860 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0812. Min Act: -0.0001

Data Index: 195148 (C4 (Web Text))

Max Activating Token Index: 854