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

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

Neuron 2605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.2084. Min Act: -0.0002

Data Index: 1144375 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.2301. Min Act: -0.0002

Data Index: 1233591 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.1745. Min Act: -0.0001

Data Index: 868457 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.1806. Min Act: -0.0002

Data Index: 660428 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.1618. Min Act: -0.0002

Data Index: 791921 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.1407. Min Act: -0.0002

Data Index: 228732 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0414. Min Act: -0.0002

Data Index: 185037 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0571. Min Act: -0.0002

Data Index: 46565 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.1034. Min Act: -0.0002

Data Index: 33397 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0136. Min Act: -0.0002

Data Index: 892821 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0403. Min Act: -0.0002

Data Index: 1191438 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0948. Min Act: -0.0002

Data Index: 803396 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0550. Min Act: -0.0002

Data Index: 687455 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0245. Min Act: -0.0002

Data Index: 643730 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0133. Min Act: -0.0002

Data Index: 536178 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.1046. Min Act: -0.0002

Data Index: 204160 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9932. Min Act: -0.0002

Data Index: 707060 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0074. Min Act: -0.0001

Data Index: 1269421 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9861. Min Act: -0.0002

Data Index: 160700 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9288. Min Act: -0.0002

Data Index: 290384 (C4 (Web Text))

Max Activating Token Index: 254