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

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

Neuron 4517 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.6200. Min Act: -0.0001

Data Index: 1176948 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.2986. Min Act: -0.0001

Data Index: 651352 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.5022. Min Act: -0.0001

Data Index: 1351314 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.3410. Min Act: -0.0001

Data Index: 79691 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.3943. Min Act: -0.0001

Data Index: 1184017 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.2861. Min Act: -0.0001

Data Index: 1028286 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.2007. Min Act: -0.0001

Data Index: 79761 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.3997. Min Act: -0.0001

Data Index: 1232139 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.2780. Min Act: -0.0001

Data Index: 854861 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.2480. Min Act: -0.0001

Data Index: 1329455 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.2079. Min Act: -0.0001

Data Index: 486856 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.2140. Min Act: -0.0001

Data Index: 160321 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.1872. Min Act: -0.0001

Data Index: 1335761 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.1655. Min Act: -0.0001

Data Index: 146306 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.2773. Min Act: -0.0001

Data Index: 990999 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.3062. Min Act: -0.0001

Data Index: 728531 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.2860. Min Act: -0.0001

Data Index: 1025118 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.0377. Min Act: -0.0001

Data Index: 1180555 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.1820. Min Act: -0.0001

Data Index: 295790 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 1.6200. Min Range: -1.6200

Max Act: 1.1131. Min Act: -0.0001

Data Index: 561701 (C4 (Web Text))

Max Activating Token Index: 212