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

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

Neuron 3624 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.2001. Min Act: -0.0000

Data Index: 419959 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1526. Min Act: -0.0000

Data Index: 576989 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1015384 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1115973 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1319. Min Act: -0.0000

Data Index: 18494 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1346443 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1065396 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1230. Min Act: -0.0000

Data Index: 239659 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1244691 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1182. Min Act: -0.0000

Data Index: 741291 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1257. Min Act: -0.0000

Data Index: 290907 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1191055 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1170. Min Act: -0.0000

Data Index: 287147 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1281. Min Act: -0.0000

Data Index: 26917 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1291592 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1204. Min Act: -0.0000

Data Index: 564313 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1233. Min Act: -0.0000

Data Index: 72768 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1271. Min Act: -0.0000

Data Index: 433933 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1174. Min Act: -0.0000

Data Index: 31801 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1301. Min Act: -0.0000

Data Index: 857879 (C4 (Web Text))

Max Activating Token Index: 903