Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3865 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4189. Min Range: -2.4189

Max Act: 2.4189. Min Act: -0.0000

Data Index: 861089 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 2.4189. Min Range: -2.4189

Max Act: 2.1221. Min Act: -0.0000

Data Index: 997044 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.9556. Min Act: -0.0000

Data Index: 800356 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.9236. Min Act: 0.0002

Data Index: 796773 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 2.4189. Min Range: -2.4189

Max Act: 2.0217. Min Act: -0.0000

Data Index: 1584005 (Python Code)

Max Activating Token Index: 336

Text #5

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.9954. Min Act: -0.0000

Data Index: 557377 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 2.4189. Min Range: -2.4189

Max Act: 2.0079. Min Act: -0.0000

Data Index: 924116 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.8790. Min Act: -0.0000

Data Index: 1069115 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.9843. Min Act: -0.0000

Data Index: 1538350 (Python Code)

Max Activating Token Index: 945

Text #9

Max Range: 2.4189. Min Range: -2.4189

Max Act: 2.0857. Min Act: -0.0000

Data Index: 665491 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 2.4189. Min Range: -2.4189

Max Act: 2.0862. Min Act: -0.0000

Data Index: 325970 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.9750. Min Act: -0.0000

Data Index: 456859 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.9650. Min Act: -0.0000

Data Index: 1107387 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.9252. Min Act: -0.0000

Data Index: 76654 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.9144. Min Act: 0.0000

Data Index: 904969 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.9119. Min Act: -0.0000

Data Index: 454447 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.8977. Min Act: -0.0000

Data Index: 1545235 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.7783. Min Act: -0.0000

Data Index: 1143434 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.8972. Min Act: -0.0000

Data Index: 490544 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 2.4189. Min Range: -2.4189

Max Act: 1.8636. Min Act: -0.0000

Data Index: 1042717 (C4 (Web Text))

Max Activating Token Index: 450