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

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

Neuron 3855 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1586857 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1425495 (Python Code)

Max Activating Token Index: 966

Text #2

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1615106 (Python Code)

Max Activating Token Index: 553

Text #3

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1467575 (Python Code)

Max Activating Token Index: 567

Text #4

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1568641 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1417607 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1493016 (Python Code)

Max Activating Token Index: 853

Text #7

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1495995 (Python Code)

Max Activating Token Index: 910

Text #8

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7598. Min Act: -0.0000

Data Index: 949746 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1546034 (Python Code)

Max Activating Token Index: 977

Text #10

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1395019 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1558248 (Python Code)

Max Activating Token Index: 446

Text #12

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6304. Min Act: -0.0000

Data Index: 327493 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1395524 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6313. Min Act: -0.0000

Data Index: 805044 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6360. Min Act: 0.0000

Data Index: 1476066 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1412401 (Python Code)

Max Activating Token Index: 482

Text #17

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1581885 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1586427 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1405396 (Python Code)

Max Activating Token Index: 744