Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1814 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0001

Data Index: 783162 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0596. Min Act: -0.0001

Data Index: 788063 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0526. Min Act: -0.0001

Data Index: 176787 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0497. Min Act: -0.0001

Data Index: 960562 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0513. Min Act: -0.0001

Data Index: 211510 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0507. Min Act: -0.0001

Data Index: 412637 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0496. Min Act: -0.0001

Data Index: 233009 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0492. Min Act: -0.0001

Data Index: 373912 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0469. Min Act: -0.0001

Data Index: 97446 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0481. Min Act: -0.0001

Data Index: 910368 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1056823 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0459. Min Act: -0.0001

Data Index: 387601 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0450. Min Act: -0.0001

Data Index: 176699 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1125808 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1314663 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0445. Min Act: -0.0001

Data Index: 369703 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0445. Min Act: -0.0001

Data Index: 978606 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0445. Min Act: -0.0001

Data Index: 752567 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0443. Min Act: -0.0001

Data Index: 1302553 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0462. Min Act: -0.0001

Data Index: 930422 (C4 (Web Text))

Max Activating Token Index: 805