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

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

Neuron 2561 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.8130. Min Act: -0.0000

Data Index: 1139453 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.6181. Min Act: -0.0001

Data Index: 1297813 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.3754. Min Act: -0.0001

Data Index: 1055679 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.4911. Min Act: -0.0000

Data Index: 133553 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.4650. Min Act: -0.0000

Data Index: 983531 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.3587. Min Act: -0.0001

Data Index: 1241990 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.5267. Min Act: -0.0000

Data Index: 279621 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.5769. Min Act: -0.0001

Data Index: 379753 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.5467. Min Act: -0.0000

Data Index: 783282 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.3929. Min Act: -0.0000

Data Index: 277718 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.3694. Min Act: -0.0000

Data Index: 803641 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.2907. Min Act: -0.0001

Data Index: 74742 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.2578. Min Act: -0.0000

Data Index: 29311 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.3478. Min Act: -0.0001

Data Index: 465473 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.2032. Min Act: -0.0000

Data Index: 276711 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.2639. Min Act: -0.0000

Data Index: 388518 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1365. Min Act: -0.0001

Data Index: 1116864 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1214. Min Act: -0.0001

Data Index: 122006 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1798. Min Act: -0.0000

Data Index: 495528 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.1858. Min Act: -0.0001

Data Index: 572460 (C4 (Web Text))

Max Activating Token Index: 882