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

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

Neuron 2895 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0228. Min Range: -2.0228

Max Act: 2.0228. Min Act: -0.0000

Data Index: 724607 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.9922. Min Act: -0.0000

Data Index: 403932 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.9417. Min Act: -0.0000

Data Index: 965490 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.7974. Min Act: -0.0000

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.6601. Min Act: -0.0000

Data Index: 839782 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.6713. Min Act: -0.0000

Data Index: 1137846 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.7132. Min Act: -0.0000

Data Index: 813500 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.7267. Min Act: -0.0000

Data Index: 188612 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.5744. Min Act: -0.0000

Data Index: 636876 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.6969. Min Act: -0.0000

Data Index: 218610 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.5801. Min Act: -0.0000

Data Index: 211234 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.7474. Min Act: -0.0000

Data Index: 1299409 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.5137. Min Act: -0.0000

Data Index: 42535 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1018608 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.5387. Min Act: -0.0000

Data Index: 104286 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.5041. Min Act: -0.0000

Data Index: 1301693 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.5517. Min Act: -0.0000

Data Index: 185097 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.4501. Min Act: -0.0000

Data Index: 98628 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.5511. Min Act: -0.0000

Data Index: 515563 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 2.0228. Min Range: -2.0228

Max Act: 1.5358. Min Act: -0.0000

Data Index: 1001656 (C4 (Web Text))

Max Activating Token Index: 598