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

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

Neuron 530 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.3153. Min Act: -0.0001

Data Index: 837033 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.3140. Min Act: -0.0001

Data Index: 665752 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.3114. Min Act: -0.0001

Data Index: 1238689 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.2704. Min Act: -0.0001

Data Index: 1572612 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.2255. Min Act: -0.0001

Data Index: 657636 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1378. Min Act: -0.0001

Data Index: 1530410 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1529. Min Act: -0.0001

Data Index: 519810 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1451. Min Act: -0.0001

Data Index: 991238 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1655. Min Act: -0.0001

Data Index: 150247 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1056. Min Act: -0.0001

Data Index: 891811 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1035. Min Act: -0.0001

Data Index: 1249827 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1195. Min Act: -0.0001

Data Index: 156426 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0430. Min Act: -0.0001

Data Index: 1040298 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1142. Min Act: -0.0001

Data Index: 302253 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0640. Min Act: -0.0001

Data Index: 147542 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0277. Min Act: -0.0001

Data Index: 961655 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1335. Min Act: -0.0001

Data Index: 678611 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0617. Min Act: -0.0001

Data Index: 1534112 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0265. Min Act: -0.0001

Data Index: 309541 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0016. Min Act: -0.0001

Data Index: 103812 (C4 (Web Text))

Max Activating Token Index: 124