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

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

Neuron 5907 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: 0.9400. Min Range: -0.9400

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1159621 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8628. Min Act: -0.0000

Data Index: 355984 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1179151 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7844. Min Act: -0.0000

Data Index: 733530 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1620692 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.9400. Min Act: -0.0000

Data Index: 422127 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8826. Min Act: -0.0000

Data Index: 663703 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1237312 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8611. Min Act: -0.0000

Data Index: 892590 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8588. Min Act: -0.0000

Data Index: 170090 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7958. Min Act: -0.0000

Data Index: 384418 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1393746 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7935. Min Act: -0.0000

Data Index: 792548 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1097178 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1326804 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1094345 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1122931 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1528624 (Python Code)

Max Activating Token Index: 828

Text #18

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1495522 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7432. Min Act: -0.0000

Data Index: 755887 (C4 (Web Text))

Max Activating Token Index: 183