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

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

Neuron 4465 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0003

Data Index: 767263 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0575. Min Act: -0.0003

Data Index: 67821 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1161955 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0500. Min Act: -0.0003

Data Index: 791761 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0505. Min Act: -0.0003

Data Index: 36115 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1049619 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0486. Min Act: -0.0003

Data Index: 42238 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0482. Min Act: -0.0003

Data Index: 180333 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0482. Min Act: -0.0003

Data Index: 80295 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0479. Min Act: -0.0003

Data Index: 970852 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1088583 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0482. Min Act: -0.0003

Data Index: 551974 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1060633 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1244238 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0517. Min Act: -0.0003

Data Index: 608681 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0467. Min Act: -0.0002

Data Index: 826156 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1219294 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0463. Min Act: -0.0003

Data Index: 221826 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0453. Min Act: -0.0003

Data Index: 5987 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0445. Min Act: -0.0003

Data Index: 949645 (C4 (Web Text))

Max Activating Token Index: 147