Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 893 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0567. Min Act: -0.0003

Data Index: 407039 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1274283 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0552. Min Act: -0.0003

Data Index: 96033 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0573. Min Act: -0.0003

Data Index: 838689 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0573. Min Act: -0.0003

Data Index: 474149 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0568. Min Act: -0.0003

Data Index: 823809 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0558. Min Act: -0.0003

Data Index: 799844 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1231000 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0592. Min Act: -0.0003

Data Index: 433595 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0513. Min Act: -0.0003

Data Index: 922226 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0566. Min Act: -0.0003

Data Index: 333820 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0540. Min Act: -0.0003

Data Index: 784691 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0558. Min Act: -0.0003

Data Index: 233689 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0529. Min Act: -0.0003

Data Index: 230524 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0538. Min Act: -0.0003

Data Index: 334559 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0492. Min Act: -0.0003

Data Index: 713966 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0522. Min Act: -0.0003

Data Index: 393460 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0538. Min Act: -0.0003

Data Index: 245811 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1107996 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0486. Min Act: -0.0003

Data Index: 73942 (C4 (Web Text))

Max Activating Token Index: 876