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

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

Neuron 4517 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6159. Min Range: -4.6159

Max Act: 4.6159. Min Act: -0.0000

Data Index: 1153791 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 4.6159. Min Range: -4.6159

Max Act: 4.5966. Min Act: -0.0000

Data Index: 381107 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 4.6159. Min Range: -4.6159

Max Act: 4.5313. Min Act: -0.0000

Data Index: 418505 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 4.6159. Min Range: -4.6159

Max Act: 4.5163. Min Act: -0.0000

Data Index: 727892 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 4.6159. Min Range: -4.6159

Max Act: 4.1837. Min Act: -0.0000

Data Index: 973829 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 4.6159. Min Range: -4.6159

Max Act: 4.1494. Min Act: -0.0000

Data Index: 1135082 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 4.6159. Min Range: -4.6159

Max Act: 4.3431. Min Act: -0.0000

Data Index: 781894 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 4.6159. Min Range: -4.6159

Max Act: 3.6264. Min Act: -0.0000

Data Index: 882891 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 4.6159. Min Range: -4.6159

Max Act: 4.0830. Min Act: -0.0000

Data Index: 15442 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 4.6159. Min Range: -4.6159

Max Act: 3.3429. Min Act: -0.0000

Data Index: 729061 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 4.6159. Min Range: -4.6159

Max Act: 3.6590. Min Act: -0.0000

Data Index: 781204 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 4.6159. Min Range: -4.6159

Max Act: 3.3736. Min Act: -0.0000

Data Index: 373716 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 4.6159. Min Range: -4.6159

Max Act: 3.1258. Min Act: -0.0000

Data Index: 1273251 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 4.6159. Min Range: -4.6159

Max Act: 3.2177. Min Act: -0.0000

Data Index: 675988 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 4.6159. Min Range: -4.6159

Max Act: 3.0506. Min Act: -0.0000

Data Index: 367549 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 4.6159. Min Range: -4.6159

Max Act: 3.3160. Min Act: -0.0000

Data Index: 1359519 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 4.6159. Min Range: -4.6159

Max Act: 2.9518. Min Act: -0.0000

Data Index: 860637 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 4.6159. Min Range: -4.6159

Max Act: 2.8067. Min Act: -0.0000

Data Index: 1146936 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 4.6159. Min Range: -4.6159

Max Act: 2.8005. Min Act: -0.0000

Data Index: 1243159 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 4.6159. Min Range: -4.6159

Max Act: 2.9371. Min Act: -0.0000

Data Index: 962220 (C4 (Web Text))

Max Activating Token Index: 458