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

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

Neuron 640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1768. Min Act: -0.0000

Data Index: 581092 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1589. Min Act: -0.0000

Data Index: 242594 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1249624 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1033940 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1408. Min Act: -0.0001

Data Index: 73735 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1282403 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1369. Min Act: -0.0000

Data Index: 70039 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1120114 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1340. Min Act: -0.0000

Data Index: 592890 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1286. Min Act: -0.0001

Data Index: 979964 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1382. Min Act: -0.0000

Data Index: 45424 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1190685 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1206. Min Act: -0.0001

Data Index: 30778 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1285. Min Act: -0.0000

Data Index: 857747 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1165264 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1213. Min Act: -0.0000

Data Index: 685979 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1302. Min Act: -0.0000

Data Index: 873853 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1065597 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1177. Min Act: -0.0000

Data Index: 460513 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1184. Min Act: -0.0000

Data Index: 16531 (C4 (Web Text))

Max Activating Token Index: 458