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

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

Neuron 601 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2965. Min Act: -0.0000

Data Index: 785810 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2906. Min Act: -0.0000

Data Index: 473227 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1276295 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1132312 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1156637 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2124. Min Act: -0.0000

Data Index: 710584 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2163. Min Act: -0.0000

Data Index: 415749 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2006. Min Act: -0.0000

Data Index: 147656 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2053. Min Act: -0.0000

Data Index: 464590 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2052. Min Act: -0.0000

Data Index: 362793 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1213496 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2049. Min Act: -0.0000

Data Index: 260035 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.1937. Min Act: -0.0000

Data Index: 899997 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1314786 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.1890. Min Act: -0.0000

Data Index: 600352 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1308659 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1275429 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.1873. Min Act: -0.0000

Data Index: 760590 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1227226 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.1830. Min Act: -0.0000

Data Index: 964222 (C4 (Web Text))

Max Activating Token Index: 568