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

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

Neuron 403 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7421. Min Act: -0.0002

Data Index: 1465631 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6985. Min Act: -0.0002

Data Index: 1369691 (Python Code)

Max Activating Token Index: 979

Text #2

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7637. Min Act: -0.0002

Data Index: 1498822 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7533. Min Act: -0.0002

Data Index: 1396135 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5094. Min Act: -0.0002

Data Index: 1531996 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6428. Min Act: -0.0002

Data Index: 1393344 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5772. Min Act: -0.0002

Data Index: 1526185 (Python Code)

Max Activating Token Index: 977

Text #7

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7605. Min Act: -0.0002

Data Index: 1396969 (Python Code)

Max Activating Token Index: 639

Text #8

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6070. Min Act: -0.0002

Data Index: 1411938 (Python Code)

Max Activating Token Index: 1022

Text #9

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6389. Min Act: -0.0002

Data Index: 1498305 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5604. Min Act: -0.0002

Data Index: 1508484 (Python Code)

Max Activating Token Index: 290

Text #11

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6275. Min Act: -0.0002

Data Index: 1498465 (Python Code)

Max Activating Token Index: 325

Text #12

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6410. Min Act: -0.0002

Data Index: 1560333 (Python Code)

Max Activating Token Index: 1007

Text #13

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6769. Min Act: -0.0002

Data Index: 1515882 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5800. Min Act: -0.0002

Data Index: 1613057 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5951. Min Act: -0.0002

Data Index: 1379502 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6468. Min Act: -0.0002

Data Index: 1534317 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6071. Min Act: -0.0002

Data Index: 1621418 (Python Code)

Max Activating Token Index: 179

Text #18

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5181. Min Act: -0.0002

Data Index: 1435631 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6271. Min Act: -0.0002

Data Index: 1384419 (Python Code)

Max Activating Token Index: 246