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

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

Neuron 1261 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: 1.4093. Min Range: -1.4093

Max Act: 1.3838. Min Act: -0.0000

Data Index: 839856 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.4093. Min Act: -0.0000

Data Index: 694908 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.2525. Min Act: -0.0000

Data Index: 93945 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.1596. Min Act: -0.0000

Data Index: 1177480 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1108638 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.3107. Min Act: -0.0000

Data Index: 64201 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.0356. Min Act: -0.0000

Data Index: 648316 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.1411. Min Act: -0.0000

Data Index: 817247 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1274336 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1148501 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.0054. Min Act: -0.0000

Data Index: 1018627 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.1299. Min Act: -0.0000

Data Index: 768414 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.1302. Min Act: -0.0000

Data Index: 363802 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.1311. Min Act: -0.0000

Data Index: 930457 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.0946. Min Act: -0.0000

Data Index: 691995 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1118598 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.0504. Min Act: -0.0000

Data Index: 200900 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.0158. Min Act: -0.0000

Data Index: 1246166 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 1.4093. Min Range: -1.4093

Max Act: 1.0363. Min Act: -0.0000

Data Index: 1038435 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 1.4093. Min Range: -1.4093

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1058601 (C4 (Web Text))

Max Activating Token Index: 783