Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1056 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0685. Min Act: -0.0003

Data Index: 935719 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0571. Min Act: -0.0003

Data Index: 55553 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0567. Min Act: -0.0002

Data Index: 212253 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0570. Min Act: -0.0003

Data Index: 653195 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0525. Min Act: -0.0004

Data Index: 401698 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0520. Min Act: -0.0003

Data Index: 270864 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0522. Min Act: -0.0003

Data Index: 662707 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0551. Min Act: -0.0003

Data Index: 989942 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0500. Min Act: -0.0003

Data Index: 102378 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0510. Min Act: -0.0003

Data Index: 174625 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0510. Min Act: -0.0004

Data Index: 190246 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0489. Min Act: -0.0003

Data Index: 237092 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0503. Min Act: -0.0003

Data Index: 376077 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0502. Min Act: -0.0003

Data Index: 151017 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0525. Min Act: -0.0003

Data Index: 586136 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0491. Min Act: -0.0003

Data Index: 464435 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0511. Min Act: -0.0004

Data Index: 743604 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0484. Min Act: -0.0003

Data Index: 190267 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0468. Min Act: -0.0003

Data Index: 756513 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0446. Min Act: -0.0003

Data Index: 71216 (C4 (Web Text))

Max Activating Token Index: 851