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

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

Neuron 171 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: 0.7306. Min Range: -0.7306

Max Act: 0.7306. Min Act: -0.0001

Data Index: 1445203 (Python Code)

Max Activating Token Index: 290

Text #1

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.7078. Min Act: -0.0001

Data Index: 48472 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6657. Min Act: -0.0001

Data Index: 1206892 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6920. Min Act: -0.0001

Data Index: 1182690 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6821. Min Act: -0.0001

Data Index: 1612889 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5860. Min Act: -0.0001

Data Index: 673616 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5270. Min Act: -0.0001

Data Index: 391699 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6090. Min Act: -0.0001

Data Index: 395485 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6069. Min Act: -0.0001

Data Index: 170673 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6205. Min Act: -0.0001

Data Index: 652299 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5751. Min Act: -0.0001

Data Index: 702643 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6033. Min Act: -0.0001

Data Index: 660147 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5876. Min Act: -0.0001

Data Index: 550052 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5738. Min Act: -0.0001

Data Index: 1307968 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5731. Min Act: -0.0001

Data Index: 1291516 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5665. Min Act: -0.0001

Data Index: 273622 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5617. Min Act: -0.0001

Data Index: 34595 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5910. Min Act: -0.0001

Data Index: 1343108 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5565. Min Act: -0.0001

Data Index: 1161592 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5587. Min Act: -0.0001

Data Index: 628980 (C4 (Web Text))

Max Activating Token Index: 7