Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 923 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0004

Data Index: 112933 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1104423 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0330. Min Act: -0.0004

Data Index: 178900 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0323. Min Act: -0.0004

Data Index: 859930 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0315. Min Act: -0.0004

Data Index: 573683 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0312. Min Act: -0.0004

Data Index: 929152 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0312. Min Act: -0.0004

Data Index: 450705 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0306. Min Act: -0.0004

Data Index: 1227977 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0302. Min Act: -0.0004

Data Index: 732720 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0300. Min Act: -0.0004

Data Index: 862379 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1053024 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0298. Min Act: -0.0004

Data Index: 1222673 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0304. Min Act: -0.0004

Data Index: 1283578 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0296. Min Act: -0.0004

Data Index: 279662 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0296. Min Act: -0.0004

Data Index: 950400 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1014233 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0289. Min Act: -0.0004

Data Index: 1045777 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0288. Min Act: -0.0004

Data Index: 365570 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0293. Min Act: -0.0004

Data Index: 840929 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0293. Min Act: -0.0004

Data Index: 869341 (C4 (Web Text))

Max Activating Token Index: 525