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

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

Neuron 2677 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.7457. Min Act: -0.0002

Data Index: 344317 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.7410. Min Act: -0.0002

Data Index: 362389 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.8136. Min Act: -0.0002

Data Index: 955907 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.7142. Min Act: -0.0002

Data Index: 637030 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.7871. Min Act: -0.0002

Data Index: 956976 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.7298. Min Act: -0.0002

Data Index: 521615 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.7705. Min Act: -0.0002

Data Index: 664370 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.7307. Min Act: -0.0002

Data Index: 207078 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6004. Min Act: -0.0002

Data Index: 383197 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6134. Min Act: -0.0002

Data Index: 236105 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.8051. Min Act: -0.0002

Data Index: 113380 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6041. Min Act: -0.0002

Data Index: 1274097 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6230. Min Act: -0.0002

Data Index: 439096 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6605. Min Act: -0.0002

Data Index: 335682 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6616. Min Act: -0.0002

Data Index: 613109 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.4620. Min Act: -0.0002

Data Index: 155121 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.5573. Min Act: -0.0002

Data Index: 358967 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.5937. Min Act: -0.0002

Data Index: 32094 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.4110. Min Act: -0.0002

Data Index: 1040207 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6280. Min Act: -0.0002

Data Index: 554054 (C4 (Web Text))

Max Activating Token Index: 451