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

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

Neuron 3405 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.6919. Min Act: -0.0001

Data Index: 1013665 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.5003. Min Act: -0.0001

Data Index: 639790 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.4276. Min Act: -0.0001

Data Index: 1329729 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3607. Min Act: -0.0001

Data Index: 868600 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3553. Min Act: -0.0001

Data Index: 556154 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3845. Min Act: -0.0001

Data Index: 892812 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3194. Min Act: -0.0001

Data Index: 779604 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3734. Min Act: -0.0000

Data Index: 623406 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3917. Min Act: -0.0001

Data Index: 1536871 (Python Code)

Max Activating Token Index: 1017

Text #9

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3428. Min Act: -0.0001

Data Index: 1391249 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3485. Min Act: -0.0001

Data Index: 786349 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3483. Min Act: -0.0001

Data Index: 684086 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3457. Min Act: -0.0001

Data Index: 798384 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.2986. Min Act: -0.0001

Data Index: 90246 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.2935. Min Act: -0.0001

Data Index: 24721 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3613. Min Act: -0.0001

Data Index: 180773 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.2890. Min Act: -0.0001

Data Index: 193415 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.2935. Min Act: -0.0001

Data Index: 1059472 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.2862. Min Act: -0.0001

Data Index: 1041240 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.6919. Min Range: -1.6919

Max Act: 1.3256. Min Act: -0.0001

Data Index: 1249186 (C4 (Web Text))

Max Activating Token Index: 228