Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3573 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.6675. Min Range: -5.6675

Max Act: 5.3932. Min Act: -0.0000

Data Index: 117341 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 5.6675. Min Range: -5.6675

Max Act: 5.6675. Min Act: -0.0000

Data Index: 433625 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 5.6675. Min Range: -5.6675

Max Act: 5.3439. Min Act: -0.0000

Data Index: 600206 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 5.6675. Min Range: -5.6675

Max Act: 5.0522. Min Act: -0.0000

Data Index: 1297999 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.8480. Min Act: -0.0000

Data Index: 122389 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.9865. Min Act: -0.0000

Data Index: 726432 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.8120. Min Act: -0.0000

Data Index: 1086560 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.9638. Min Act: -0.0000

Data Index: 10589 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.1183. Min Act: -0.0000

Data Index: 1350329 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.8151. Min Act: -0.0000

Data Index: 1328130 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.2751. Min Act: -0.0000

Data Index: 1221149 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.2615. Min Act: -0.0000

Data Index: 746595 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 5.6675. Min Range: -5.6675

Max Act: 3.7421. Min Act: -0.0000

Data Index: 344147 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.1800. Min Act: -0.0000

Data Index: 1133543 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 5.6675. Min Range: -5.6675

Max Act: 3.9648. Min Act: -0.0000

Data Index: 1019858 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 5.6675. Min Range: -5.6675

Max Act: 3.7822. Min Act: -0.0000

Data Index: 195666 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 5.6675. Min Range: -5.6675

Max Act: 3.9189. Min Act: -0.0000

Data Index: 988571 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.0640. Min Act: -0.0000

Data Index: 539991 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 5.6675. Min Range: -5.6675

Max Act: 4.0279. Min Act: -0.0000

Data Index: 632786 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 5.6675. Min Range: -5.6675

Max Act: 3.6800. Min Act: -0.0000

Data Index: 217836 (C4 (Web Text))

Max Activating Token Index: 320