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

Dataset: The Pile

Neuron 3010 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7243. Min Act: -0.0000

Data Index: 619800 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6087. Min Act: -0.0000

Data Index: 692841 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1126213 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4219. Min Act: -0.0000

Data Index: 204009 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1361528 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1978081 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4130. Min Act: -0.0000

Data Index: 131119 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4411. Min Act: -0.0000

Data Index: 76245 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4228. Min Act: -0.0000

Data Index: 112765 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1256506 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4214. Min Act: -0.0000

Data Index: 400149 (The Pile)

Max Activating Token Index: 238

Text #11

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1944626 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4335. Min Act: -0.0000

Data Index: 322679 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4152. Min Act: -0.0000

Data Index: 207219 (The Pile)

Max Activating Token Index: 701

Text #14

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1221312 (The Pile)

Max Activating Token Index: 815

Text #15

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4242. Min Act: 0.0000

Data Index: 1468276 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4344. Min Act: 0.0000

Data Index: 1148191 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1275473 (The Pile)

Max Activating Token Index: 216

Text #18

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4068. Min Act: -0.0000

Data Index: 37603 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.3915. Min Act: -0.0000

Data Index: 987250 (The Pile)

Max Activating Token Index: 972