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

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

Neuron 47 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: 1.1143. Min Range: -1.1143

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1563603 (Python Code)

Max Activating Token Index: 578

Text #1

Max Range: 1.1143. Min Range: -1.1143

Max Act: 1.0114. Min Act: -0.0000

Data Index: 91273 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.1143. Min Range: -1.1143

Max Act: 1.0273. Min Act: -0.0000

Data Index: 44622 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1165884 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1103152 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.8960. Min Act: -0.0000

Data Index: 998912 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.8794. Min Act: -0.0000

Data Index: 740078 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1598653 (Python Code)

Max Activating Token Index: 390

Text #8

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1499096 (Python Code)

Max Activating Token Index: 252

Text #9

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.8130. Min Act: -0.0000

Data Index: 930186 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1307912 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1173276 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7597. Min Act: -0.0000

Data Index: 940356 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7498. Min Act: -0.0000

Data Index: 996622 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7258. Min Act: -0.0000

Data Index: 474939 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1147353 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1462189 (Python Code)

Max Activating Token Index: 636

Text #17

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7154. Min Act: -0.0000

Data Index: 521346 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6522. Min Act: -0.0000

Data Index: 225929 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1377046 (Python Code)

Max Activating Token Index: 651