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

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

Neuron 2056 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: 1.1254. Min Range: -1.1254

Max Act: 1.1254. Min Act: -0.0000

Data Index: 877982 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 1.1254. Min Range: -1.1254

Max Act: 1.0497. Min Act: -0.0000

Data Index: 414354 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.1254. Min Range: -1.1254

Max Act: 1.0175. Min Act: -0.0000

Data Index: 235068 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 1.1254. Min Range: -1.1254

Max Act: 1.0596. Min Act: -0.0000

Data Index: 197794 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 1.1254. Min Range: -1.1254

Max Act: 1.0006. Min Act: -0.0000

Data Index: 200721 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1046957 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 1.1254. Min Range: -1.1254

Max Act: 1.0345. Min Act: -0.0000

Data Index: 335822 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.1254. Min Range: -1.1254

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1540687 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1126783 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1341990 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.8685. Min Act: -0.0000

Data Index: 446301 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.9468. Min Act: -0.0000

Data Index: 174767 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1272304 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1004453 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.9244. Min Act: -0.0000

Data Index: 281673 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.8767. Min Act: -0.0000

Data Index: 835071 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.8563. Min Act: -0.0000

Data Index: 30247 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.9058. Min Act: -0.0000

Data Index: 443273 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.8763. Min Act: -0.0000

Data Index: 528280 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.1254. Min Range: -1.1254

Max Act: 0.8053. Min Act: -0.0000

Data Index: 630028 (C4 (Web Text))

Max Activating Token Index: 46