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

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

Neuron 3691 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.5093. Min Act: -0.0000

Data Index: 866648 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.4787. Min Act: -0.0000

Data Index: 617074 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.2939. Min Act: -0.0000

Data Index: 159100 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.3199. Min Act: -0.0000

Data Index: 828523 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1385890 (Python Code)

Max Activating Token Index: 933

Text #5

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1636371 (Python Code)

Max Activating Token Index: 961

Text #6

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.2246. Min Act: -0.0000

Data Index: 763742 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.1378. Min Act: -0.0000

Data Index: 780934 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.1092. Min Act: -0.0000

Data Index: 819070 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.1326. Min Act: -0.0000

Data Index: 492321 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1397071 (Python Code)

Max Activating Token Index: 448

Text #11

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.0478. Min Act: -0.0000

Data Index: 888212 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1151052 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.0939. Min Act: -0.0000

Data Index: 1219299 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.1272. Min Act: -0.0000

Data Index: 647967 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.0979. Min Act: -0.0000

Data Index: 999036 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.5093. Min Range: -1.5093

Max Act: 0.9963. Min Act: -0.0000

Data Index: 983404 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.0567. Min Act: -0.0000

Data Index: 510329 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1521638 (Python Code)

Max Activating Token Index: 832

Text #19

Max Range: 1.5093. Min Range: -1.5093

Max Act: 1.0579. Min Act: -0.0000

Data Index: 991134 (C4 (Web Text))

Max Activating Token Index: 850