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

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

Neuron 5034 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3699. Min Act: -0.0000

Data Index: 20561 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3304. Min Act: -0.0000

Data Index: 1151677 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3191. Min Act: -0.0000

Data Index: 755535 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2339. Min Act: -0.0000

Data Index: 311946 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2340. Min Act: -0.0000

Data Index: 168911 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1187279 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2203. Min Act: -0.0000

Data Index: 812800 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2191. Min Act: -0.0000

Data Index: 256850 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2038. Min Act: -0.0000

Data Index: 46355 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2085. Min Act: -0.0000

Data Index: 661206 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1309861 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1055583 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2106. Min Act: -0.0000

Data Index: 348059 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2023. Min Act: -0.0000

Data Index: 919581 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1227821 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2095. Min Act: -0.0000

Data Index: 918269 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2012. Min Act: -0.0000

Data Index: 852756 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.1911. Min Act: -0.0000

Data Index: 296355 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.1897. Min Act: -0.0000

Data Index: 849057 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.1942. Min Act: -0.0000

Data Index: 387918 (C4 (Web Text))

Max Activating Token Index: 752