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

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

Neuron 3214 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5198. Min Act: -0.0000

Data Index: 1424355 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.0078. Min Act: -0.0000

Data Index: 1525731 (Python Code)

Max Activating Token Index: 525

Text #2

Max Range: 3.6941. Min Range: -3.6941

Max Act: 2.6880. Min Act: -0.0000

Data Index: 1502314 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 3.6941. Min Range: -3.6941

Max Act: 2.6665. Min Act: -0.0000

Data Index: 1365915 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6941. Min Act: -0.0000

Data Index: 1627815 (Python Code)

Max Activating Token Index: 400

Text #5

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.1039. Min Act: -0.0000

Data Index: 1602699 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.2454. Min Act: -0.0000

Data Index: 1574528 (Python Code)

Max Activating Token Index: 160

Text #7

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5658. Min Act: -0.0000

Data Index: 1598800 (Python Code)

Max Activating Token Index: 197

Text #8

Max Range: 3.6941. Min Range: -3.6941

Max Act: 2.8584. Min Act: -0.0000

Data Index: 1493477 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.1639. Min Act: -0.0000

Data Index: 1541178 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.3145. Min Act: -0.0000

Data Index: 1387645 (Python Code)

Max Activating Token Index: 415

Text #11

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5863. Min Act: -0.0000

Data Index: 1485476 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5892. Min Act: -0.0000

Data Index: 1481128 (Python Code)

Max Activating Token Index: 263

Text #13

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.1007. Min Act: -0.0000

Data Index: 1409730 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 3.6941. Min Range: -3.6941

Max Act: 2.5816. Min Act: -0.0000

Data Index: 1544207 (Python Code)

Max Activating Token Index: 229

Text #15

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.1063. Min Act: -0.0000

Data Index: 1434635 (Python Code)

Max Activating Token Index: 107

Text #16

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.2494. Min Act: -0.0000

Data Index: 1580278 (Python Code)

Max Activating Token Index: 326

Text #17

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.2249. Min Act: -0.0000

Data Index: 1612306 (Python Code)

Max Activating Token Index: 302

Text #18

Max Range: 3.6941. Min Range: -3.6941

Max Act: 2.8260. Min Act: -0.0000

Data Index: 1545607 (Python Code)

Max Activating Token Index: 346

Text #19

Max Range: 3.6941. Min Range: -3.6941

Max Act: 2.8225. Min Act: -0.0000

Data Index: 1651202 (Python Code)

Max Activating Token Index: 224