Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3965 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.5298. Min Act: -0.0000

Data Index: 1079009 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 5.1162. Min Range: -5.1162

Max Act: 5.1162. Min Act: -0.0000

Data Index: 149483 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.7200. Min Act: -0.0000

Data Index: 560613 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.5316. Min Act: -0.0000

Data Index: 1105201 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.4842. Min Act: -0.0000

Data Index: 138672 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.9699. Min Act: -0.0000

Data Index: 634124 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.4386. Min Act: -0.0000

Data Index: 73038 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.5722. Min Act: -0.0000

Data Index: 1281201 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.3397. Min Act: -0.0000

Data Index: 1049961 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.0973. Min Act: -0.0000

Data Index: 394754 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 5.1162. Min Range: -5.1162

Max Act: 3.9158. Min Act: -0.0000

Data Index: 1050587 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.4241. Min Act: -0.0000

Data Index: 969351 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.0248. Min Act: -0.0000

Data Index: 701985 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.1785. Min Act: -0.0000

Data Index: 410360 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.1880. Min Act: -0.0000

Data Index: 912117 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.1630. Min Act: -0.0000

Data Index: 297123 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.0775. Min Act: -0.0000

Data Index: 525792 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 5.1162. Min Range: -5.1162

Max Act: 3.9029. Min Act: -0.0000

Data Index: 1217832 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 5.1162. Min Range: -5.1162

Max Act: 3.7831. Min Act: -0.0000

Data Index: 184772 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 5.1162. Min Range: -5.1162

Max Act: 4.0124. Min Act: -0.0000

Data Index: 313918 (C4 (Web Text))

Max Activating Token Index: 193