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

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

Neuron 3739 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: 2.0144. Min Range: -2.0144

Max Act: 2.0144. Min Act: -0.0000

Data Index: 696421 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.8373. Min Act: -0.0000

Data Index: 958182 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.8901. Min Act: -0.0000

Data Index: 175159 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.7220. Min Act: -0.0000

Data Index: 488189 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.6800. Min Act: -0.0000

Data Index: 926909 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1022348 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.5048. Min Act: -0.0000

Data Index: 755035 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.5802. Min Act: -0.0000

Data Index: 1298989 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.4528. Min Act: -0.0000

Data Index: 871346 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.5164. Min Act: -0.0000

Data Index: 286853 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.5221. Min Act: -0.0000

Data Index: 978603 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.4362. Min Act: -0.0000

Data Index: 63184 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.4239. Min Act: -0.0000

Data Index: 1065437 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.3172. Min Act: -0.0000

Data Index: 10163 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1348787 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.3966. Min Act: -0.0000

Data Index: 34843 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.3852. Min Act: -0.0000

Data Index: 1094801 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.2949. Min Act: -0.0000

Data Index: 1359794 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.3382. Min Act: -0.0000

Data Index: 705716 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 2.0144. Min Range: -2.0144

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1023761 (C4 (Web Text))

Max Activating Token Index: 314