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

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

Neuron 3061 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2748. Min Act: -0.0000

Data Index: 909919 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1655410 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2408. Min Act: -0.0000

Data Index: 955566 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2240. Min Act: -0.0000

Data Index: 609993 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2206. Min Act: -0.0000

Data Index: 520658 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2274. Min Act: -0.0000

Data Index: 870051 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1013643 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2251. Min Act: -0.0000

Data Index: 890490 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2240. Min Act: -0.0000

Data Index: 84751 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1653419 (Python Code)

Max Activating Token Index: 230

Text #10

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2220. Min Act: -0.0000

Data Index: 63575 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1989. Min Act: -0.0000

Data Index: 537126 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1193259 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1062737 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1074859 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1076146 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1974. Min Act: -0.0000

Data Index: 745090 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1934. Min Act: -0.0000

Data Index: 1529030 (Python Code)

Max Activating Token Index: 80

Text #18

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1564305 (Python Code)

Max Activating Token Index: 884

Text #19

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2118. Min Act: -0.0000

Data Index: 661085 (C4 (Web Text))

Max Activating Token Index: 308