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

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

Neuron 4768 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1458. Min Range: -2.1458

Max Act: 2.1458. Min Act: -0.0000

Data Index: 7899 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.7073. Min Act: -0.0000

Data Index: 1333790 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6011. Min Act: -0.0000

Data Index: 425693 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6611. Min Act: -0.0000

Data Index: 1199237 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.5700. Min Act: -0.0000

Data Index: 1253214 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.5744. Min Act: -0.0000

Data Index: 784769 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.6590. Min Act: -0.0000

Data Index: 1120717 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.5371. Min Act: -0.0000

Data Index: 145342 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.5316. Min Act: -0.0000

Data Index: 177467 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.5192. Min Act: -0.0000

Data Index: 98227 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1349693 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.4342. Min Act: -0.0000

Data Index: 1127133 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1224058 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.3450. Min Act: -0.0000

Data Index: 643569 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.3208. Min Act: -0.0000

Data Index: 410018 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.4777. Min Act: -0.0000

Data Index: 1089585 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.3968. Min Act: -0.0000

Data Index: 144524 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.3766. Min Act: -0.0000

Data Index: 370867 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.4101. Min Act: -0.0000

Data Index: 671759 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 2.1458. Min Range: -2.1458

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1172349 (C4 (Web Text))

Max Activating Token Index: 54