Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3032 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1651018 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.0317. Min Act: -0.0000

Data Index: 207814 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.9162. Min Act: -0.0000

Data Index: 101888 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.9213. Min Act: -0.0000

Data Index: 244648 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.8449. Min Act: -0.0000

Data Index: 621281 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7985. Min Act: -0.0000

Data Index: 471273 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1104750 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1123726 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.8586. Min Act: -0.0000

Data Index: 537032 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.8214. Min Act: -0.0000

Data Index: 983918 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1102688 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1406856 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1601771 (The Pile)

Max Activating Token Index: 68

Text #13

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1385155 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7570. Min Act: -0.0000

Data Index: 882748 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7401. Min Act: -0.0000

Data Index: 287858 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1360342 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7924. Min Act: -0.0000

Data Index: 418639 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7593. Min Act: -0.0000

Data Index: 194060 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 1.4162. Min Range: -1.4162

Max Act: 0.7730. Min Act: -0.0000

Data Index: 986330 (The Pile)

Max Activating Token Index: 267