Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3576 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1593. Min Act: -0.0001

Data Index: 381996 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1403. Min Act: -0.0001

Data Index: 339390 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1508. Min Act: -0.0001

Data Index: 375529 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1204. Min Act: -0.0001

Data Index: 286807 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1308. Min Act: -0.0001

Data Index: 649462 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1343. Min Act: -0.0001

Data Index: 23901 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1146. Min Act: -0.0001

Data Index: 3252 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1312. Min Act: -0.0001

Data Index: 34606 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1260. Min Act: -0.0001

Data Index: 91281 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1327295 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1218. Min Act: -0.0001

Data Index: 708459 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1300. Min Act: -0.0001

Data Index: 459941 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1212. Min Act: -0.0001

Data Index: 338629 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1155. Min Act: -0.0001

Data Index: 109147 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1176262 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1111111 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1330. Min Act: -0.0001

Data Index: 303747 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1050745 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1142. Min Act: -0.0001

Data Index: 89221 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1177. Min Act: -0.0001

Data Index: 845291 (C4 (Web Text))

Max Activating Token Index: 472