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

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

Neuron 3616 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8296. Min Range: -4.8296

Max Act: 4.8296. Min Act: -0.0000

Data Index: 162113 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 4.8296. Min Range: -4.8296

Max Act: 4.7591. Min Act: -0.0000

Data Index: 77089 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 4.8296. Min Range: -4.8296

Max Act: 4.5452. Min Act: -0.0000

Data Index: 851376 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 4.8296. Min Range: -4.8296

Max Act: 4.5828. Min Act: -0.0000

Data Index: 203327 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 4.8296. Min Range: -4.8296

Max Act: 4.3770. Min Act: -0.0000

Data Index: 912995 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 4.8296. Min Range: -4.8296

Max Act: 3.8988. Min Act: -0.0000

Data Index: 1173810 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 4.8296. Min Range: -4.8296

Max Act: 4.0466. Min Act: -0.0000

Data Index: 1177776 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 4.8296. Min Range: -4.8296

Max Act: 3.7221. Min Act: -0.0000

Data Index: 783518 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 4.8296. Min Range: -4.8296

Max Act: 3.5239. Min Act: -0.0000

Data Index: 995116 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.9522. Min Act: -0.0000

Data Index: 798891 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.9025. Min Act: -0.0000

Data Index: 644140 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.9230. Min Act: -0.0000

Data Index: 1094256 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.7536. Min Act: -0.0000

Data Index: 1225275 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 4.8296. Min Range: -4.8296

Max Act: 3.0246. Min Act: -0.0000

Data Index: 794165 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.8827. Min Act: -0.0000

Data Index: 1131369 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.7257. Min Act: -0.0000

Data Index: 934875 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.8918. Min Act: -0.0000

Data Index: 337616 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.6305. Min Act: -0.0000

Data Index: 1070228 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.7658. Min Act: -0.0000

Data Index: 2466 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 4.8296. Min Range: -4.8296

Max Act: 2.5994. Min Act: -0.0000

Data Index: 1276241 (C4 (Web Text))

Max Activating Token Index: 580