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

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

Neuron 5119 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: 0.2610. Min Range: -0.2610

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1461078 (Python Code)

Max Activating Token Index: 442

Text #1

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2563. Min Act: -0.0000

Data Index: 592095 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2260. Min Act: -0.0001

Data Index: 1537566 (Python Code)

Max Activating Token Index: 720

Text #3

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1571260 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2343. Min Act: -0.0001

Data Index: 1493415 (Python Code)

Max Activating Token Index: 969

Text #5

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2169. Min Act: 0.0000

Data Index: 888133 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1622831 (Python Code)

Max Activating Token Index: 483

Text #7

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1373730 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1428339 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2059. Min Act: -0.0000

Data Index: 991265 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2037. Min Act: -0.0000

Data Index: 149409 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2028. Min Act: -0.0000

Data Index: 967099 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1448214 (Python Code)

Max Activating Token Index: 266

Text #13

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1391717 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1912. Min Act: -0.0000

Data Index: 610558 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1911. Min Act: -0.0000

Data Index: 591368 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1816. Min Act: -0.0000

Data Index: 649771 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1754. Min Act: -0.0000

Data Index: 354399 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1783. Min Act: -0.0000

Data Index: 950094 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1759. Min Act: -0.0000

Data Index: 393240 (C4 (Web Text))

Max Activating Token Index: 18