Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5699 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1581. Min Act: -0.0001

Data Index: 47468 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1593. Min Act: -0.0001

Data Index: 11028 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1318. Min Act: -0.0001

Data Index: 348599 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1325. Min Act: -0.0001

Data Index: 947913 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1472. Min Act: -0.0001

Data Index: 552590 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1537. Min Act: -0.0001

Data Index: 887090 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1348. Min Act: -0.0001

Data Index: 895274 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1122928 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1568. Min Act: -0.0001

Data Index: 212778 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1517. Min Act: -0.0001

Data Index: 770622 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1240. Min Act: -0.0001

Data Index: 100441 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1222. Min Act: -0.0001

Data Index: 127242 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1074354 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1266. Min Act: -0.0001

Data Index: 934446 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1424. Min Act: -0.0001

Data Index: 702375 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1281. Min Act: -0.0001

Data Index: 509773 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1343864 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1124. Min Act: -0.0001

Data Index: 846010 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1162. Min Act: -0.0001

Data Index: 845983 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1254. Min Act: -0.0001

Data Index: 776254 (C4 (Web Text))

Max Activating Token Index: 14