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

Dataset: The Pile

Neuron 3874 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.5183. Min Act: -0.0000

Data Index: 1589438 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.3650. Min Act: -0.0000

Data Index: 217712 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1961070 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.4192. Min Act: -0.0000

Data Index: 261123 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1949424 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1266172 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1299325 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.1768. Min Act: -0.0000

Data Index: 839975 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1786139 (The Pile)

Max Activating Token Index: 730

Text #9

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.2387. Min Act: -0.0000

Data Index: 1046379 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1032105 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.2454. Min Act: -0.0000

Data Index: 188726 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.2203. Min Act: -0.0000

Data Index: 642505 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1591650 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1184143 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.2003. Min Act: -0.0000

Data Index: 1125718 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1283761 (The Pile)

Max Activating Token Index: 140

Text #17

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.1983. Min Act: -0.0000

Data Index: 337420 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1704977 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.5183. Min Range: -1.5183

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1253109 (The Pile)

Max Activating Token Index: 455