Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1542 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1152870 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0484. Min Act: -0.0002

Data Index: 870263 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0458. Min Act: -0.0002

Data Index: 835056 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0460. Min Act: -0.0002

Data Index: 828810 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0475. Min Act: -0.0001

Data Index: 340180 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0481. Min Act: -0.0002

Data Index: 176706 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0478. Min Act: -0.0001

Data Index: 421982 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0470. Min Act: -0.0001

Data Index: 382060 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0428. Min Act: -0.0002

Data Index: 687065 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1174232 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1210564 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1260757 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1331279 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0421. Min Act: -0.0001

Data Index: 915653 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1349136 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0413. Min Act: -0.0001

Data Index: 824648 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1068970 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0421. Min Act: -0.0001

Data Index: 410907 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0416. Min Act: -0.0000

Data Index: 199352 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0415. Min Act: -0.0002

Data Index: 101140 (C4 (Web Text))

Max Activating Token Index: 640