Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2398 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1585. Min Range: -1.1585

Max Act: 1.1585. Min Act: -0.0000

Data Index: 398324 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8010. Min Act: -0.0000

Data Index: 316192 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8438. Min Act: -0.0000

Data Index: 818337 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8417. Min Act: -0.0000

Data Index: 998564 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8882. Min Act: -0.0000

Data Index: 69976 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8079. Min Act: -0.0000

Data Index: 790176 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8216. Min Act: -0.0000

Data Index: 511095 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1148367 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1156607 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.7829. Min Act: -0.0000

Data Index: 936128 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1285151 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.7360. Min Act: -0.0000

Data Index: 922793 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.7833. Min Act: -0.0000

Data Index: 376284 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.7936. Min Act: -0.0000

Data Index: 178310 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8181. Min Act: -0.0000

Data Index: 864193 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1069099 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8259. Min Act: -0.0000

Data Index: 477419 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.7553. Min Act: -0.0000

Data Index: 945288 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.7586. Min Act: -0.0000

Data Index: 153934 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.1585. Min Range: -1.1585

Max Act: 0.8019. Min Act: -0.0000

Data Index: 843490 (C4 (Web Text))

Max Activating Token Index: 392