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

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

Neuron 1955 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3159. Min Range: -2.3159

Max Act: 2.3159. Min Act: -0.0000

Data Index: 853570 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.1987. Min Act: -0.0000

Data Index: 960822 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.1109. Min Act: -0.0000

Data Index: 880480 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.0663. Min Act: -0.0000

Data Index: 693424 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.0316. Min Act: -0.0000

Data Index: 971343 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.0063. Min Act: -0.0000

Data Index: 44730 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 2.3159. Min Range: -2.3159

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1255717 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.9095. Min Act: -0.0000

Data Index: 808954 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.9934. Min Act: -0.0000

Data Index: 349237 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.9313. Min Act: -0.0000

Data Index: 110792 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.9170. Min Act: -0.0000

Data Index: 486734 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.9166. Min Act: -0.0000

Data Index: 515253 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.9179. Min Act: -0.0000

Data Index: 295991 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.8903. Min Act: -0.0000

Data Index: 738060 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1303245 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.9112. Min Act: -0.0000

Data Index: 7350 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.9166. Min Act: -0.0000

Data Index: 777451 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.8835. Min Act: -0.0000

Data Index: 466401 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.9111. Min Act: -0.0000

Data Index: 54824 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 2.3159. Min Range: -2.3159

Max Act: 0.8678. Min Act: -0.0000

Data Index: 831088 (C4 (Web Text))

Max Activating Token Index: 226