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

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

Neuron 2114 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0205. Min Range: -1.0205

Max Act: 1.0132. Min Act: -0.0001

Data Index: 1323189 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9727. Min Act: -0.0001

Data Index: 416970 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9322. Min Act: -0.0001

Data Index: 1150901 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 1.0205. Min Range: -1.0205

Max Act: 1.0205. Min Act: -0.0001

Data Index: 319715 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9492. Min Act: -0.0001

Data Index: 570119 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9462. Min Act: -0.0001

Data Index: 541619 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9828. Min Act: -0.0001

Data Index: 599293 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9491. Min Act: -0.0001

Data Index: 754941 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9540. Min Act: -0.0001

Data Index: 851850 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9919. Min Act: -0.0001

Data Index: 1265149 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9268. Min Act: -0.0001

Data Index: 324541 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9622. Min Act: -0.0001

Data Index: 1489416 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1000 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8514. Min Act: -0.0001

Data Index: 238584 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.9026. Min Act: -0.0001

Data Index: 642968 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8654. Min Act: -0.0001

Data Index: 1460870 (Python Code)

Max Activating Token Index: 120

Text #16

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1570865 (Python Code)

Max Activating Token Index: 535

Text #17

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8948. Min Act: -0.0001

Data Index: 864983 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8294. Min Act: -0.0001

Data Index: 1170319 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8031. Min Act: -0.0001

Data Index: 1438132 (Python Code)

Max Activating Token Index: 779