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

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

Neuron 3749 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8834. Min Act: -0.0000

Data Index: 909701 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1008809 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1269995 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.9087. Min Act: -0.0000

Data Index: 248284 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8512. Min Act: 0.0000

Data Index: 1076380 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1083119 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8814. Min Act: -0.0000

Data Index: 350097 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8812. Min Act: -0.0000

Data Index: 677461 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1085912 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8573. Min Act: -0.0000

Data Index: 630213 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1231440 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7993. Min Act: -0.0000

Data Index: 21617 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1305305 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7947. Min Act: -0.0000

Data Index: 882325 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7622. Min Act: -0.0000

Data Index: 794529 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7644. Min Act: -0.0000

Data Index: 510345 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1049030 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7491. Min Act: -0.0000

Data Index: 522410 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7624. Min Act: 0.0000

Data Index: 1008001 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7633. Min Act: -0.0000

Data Index: 905034 (C4 (Web Text))

Max Activating Token Index: 11