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

Dataset: The Pile

Neuron 2642 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: 1.2301. Min Range: -1.2301

Max Act: 1.2301. Min Act: -0.0000

Data Index: 1683291 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.8653. Min Act: -0.0000

Data Index: 711986 (The Pile)

Max Activating Token Index: 177

Text #2

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9071. Min Act: -0.0000

Data Index: 797912 (The Pile)

Max Activating Token Index: 130

Text #3

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.8970. Min Act: -0.0000

Data Index: 598891 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.8400. Min Act: -0.0000

Data Index: 523461 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1375963 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1340469 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1652229 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.7087. Min Act: -0.0000

Data Index: 401469 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1947579 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1145499 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.7592. Min Act: -0.0000

Data Index: 142989 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1465136 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1068966 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.6941. Min Act: -0.0000

Data Index: 121036 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.6917. Min Act: -0.0000

Data Index: 317786 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1392330 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1504989 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.5788. Min Act: -0.0000

Data Index: 92045 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1711273 (The Pile)

Max Activating Token Index: 202