Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1398 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.6138. Min Act: -0.0003

Data Index: 1365538 (Python Code)

Max Activating Token Index: 457

Text #1

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5633. Min Act: -0.0003

Data Index: 1605102 (Python Code)

Max Activating Token Index: 494

Text #2

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5335. Min Act: -0.0003

Data Index: 1557462 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5291. Min Act: -0.0003

Data Index: 1491063 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5308. Min Act: -0.0003

Data Index: 1553398 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5194. Min Act: -0.0003

Data Index: 1607940 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5098. Min Act: -0.0003

Data Index: 1583079 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4881. Min Act: -0.0003

Data Index: 1647532 (Python Code)

Max Activating Token Index: 148

Text #8

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5391. Min Act: -0.0003

Data Index: 1567385 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4956. Min Act: -0.0003

Data Index: 1625703 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4701. Min Act: -0.0003

Data Index: 1505150 (Python Code)

Max Activating Token Index: 245

Text #11

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5124. Min Act: -0.0003

Data Index: 1510636 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4318. Min Act: -0.0003

Data Index: 1433951 (Python Code)

Max Activating Token Index: 496

Text #13

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4824. Min Act: -0.0003

Data Index: 1645620 (Python Code)

Max Activating Token Index: 155

Text #14

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4316. Min Act: -0.0003

Data Index: 1525715 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4187. Min Act: -0.0003

Data Index: 1481476 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3250. Min Act: -0.0003

Data Index: 1641158 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4703. Min Act: -0.0003

Data Index: 1502159 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4563. Min Act: -0.0003

Data Index: 1523938 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5220. Min Act: -0.0003

Data Index: 1480851 (Python Code)

Max Activating Token Index: 781