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

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

Neuron 1568 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: 0.1463. Min Range: -0.1463

Max Act: 0.1457. Min Act: -0.0001

Data Index: 343457 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0001

Data Index: 491488 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1203558 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1242614 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1330. Min Act: -0.0001

Data Index: 538776 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1600712 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1104429 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1291596 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1404112 (Python Code)

Max Activating Token Index: 603

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1567890 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1000430 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1193. Min Act: -0.0001

Data Index: 452515 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1183. Min Act: -0.0001

Data Index: 215859 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1188. Min Act: -0.0001

Data Index: 569305 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1508451 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1508050 (Python Code)

Max Activating Token Index: 655

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1108801 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1124. Min Act: -0.0000

Data Index: 100259 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1356367 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1649060 (Python Code)

Max Activating Token Index: 419