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

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

Neuron 1258 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.3158. Min Act: -0.0000

Data Index: 321564 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.0768. Min Act: -0.0000

Data Index: 791258 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.2275. Min Act: -0.0000

Data Index: 310028 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1158354 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.2821. Min Act: -0.0000

Data Index: 529013 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1120562 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.1880. Min Act: -0.0000

Data Index: 657492 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1271168 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.0595. Min Act: -0.0000

Data Index: 131121 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1290698 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.2035. Min Act: -0.0000

Data Index: 684837 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.1410. Min Act: -0.0000

Data Index: 279252 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.1030. Min Act: -0.0000

Data Index: 331097 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.0443. Min Act: -0.0000

Data Index: 662192 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1037219 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9842. Min Act: -0.0000

Data Index: 19824 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.1284. Min Act: -0.0000

Data Index: 295679 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.0729. Min Act: -0.0000

Data Index: 95591 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1042007 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9162. Min Act: -0.0000

Data Index: 422422 (C4 (Web Text))

Max Activating Token Index: 792