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

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

Neuron 1060 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5979. Min Act: -0.0000

Data Index: 819679 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.6511. Min Act: -0.0000

Data Index: 356986 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.4045. Min Act: -0.0000

Data Index: 759989 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1197834 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.3910. Min Act: -0.0000

Data Index: 928946 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1117516 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.3440. Min Act: -0.0000

Data Index: 675062 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.1675. Min Act: -0.0000

Data Index: 411992 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.2664. Min Act: -0.0000

Data Index: 832990 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1321860 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.1681. Min Act: -0.0000

Data Index: 257763 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1306515 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.1521. Min Act: -0.0000

Data Index: 75321 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.2522. Min Act: -0.0000

Data Index: 257516 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.1789. Min Act: -0.0000

Data Index: 752612 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.1017. Min Act: -0.0000

Data Index: 1019538 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.0593. Min Act: -0.0000

Data Index: 959157 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.1481. Min Act: -0.0000

Data Index: 597045 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.1037. Min Act: -0.0000

Data Index: 150387 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 2.5979. Min Range: -2.5979

Max Act: 1.0558. Min Act: -0.0000

Data Index: 512690 (C4 (Web Text))

Max Activating Token Index: 416