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

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

Neuron 2179 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4722. Min Range: -1.4722

Max Act: 1.4722. Min Act: -0.0000

Data Index: 700881 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.4722. Min Range: -1.4722

Max Act: 1.4629. Min Act: -0.0000

Data Index: 240761 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 1.4722. Min Range: -1.4722

Max Act: 1.2279. Min Act: -0.0000

Data Index: 998279 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.4722. Min Range: -1.4722

Max Act: 1.0994. Min Act: -0.0000

Data Index: 727163 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 1.4722. Min Range: -1.4722

Max Act: 1.0219. Min Act: -0.0000

Data Index: 829118 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 1.4722. Min Range: -1.4722

Max Act: 1.0124. Min Act: -0.0000

Data Index: 794243 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1293816 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.9508. Min Act: -0.0000

Data Index: 396559 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.4722. Min Range: -1.4722

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1041552 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.9328. Min Act: -0.0000

Data Index: 504157 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1100042 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.9661. Min Act: -0.0000

Data Index: 691239 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.9164. Min Act: -0.0000

Data Index: 349055 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.9143. Min Act: -0.0000

Data Index: 616067 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.9127. Min Act: -0.0000

Data Index: 383374 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.8482. Min Act: 0.0000

Data Index: 445980 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.8967. Min Act: -0.0000

Data Index: 988113 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.8393. Min Act: -0.0000

Data Index: 411460 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1047529 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 1.4722. Min Range: -1.4722

Max Act: 0.8221. Min Act: -0.0000

Data Index: 216569 (C4 (Web Text))

Max Activating Token Index: 258