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

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

Neuron 4953 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2488. Min Range: -2.2488

Max Act: 2.2488. Min Act: -0.0000

Data Index: 632314 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9241. Min Act: -0.0000

Data Index: 222356 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.8122. Min Act: -0.0000

Data Index: 1202976 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6623. Min Act: -0.0000

Data Index: 200724 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.5419. Min Act: -0.0000

Data Index: 798472 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6206. Min Act: -0.0000

Data Index: 387413 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6070. Min Act: -0.0000

Data Index: 693492 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.7077. Min Act: -0.0000

Data Index: 318384 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1078267 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6527. Min Act: -0.0000

Data Index: 396700 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.5358. Min Act: -0.0000

Data Index: 585156 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.3564. Min Act: -0.0000

Data Index: 424739 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6053. Min Act: -0.0000

Data Index: 248545 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1207559 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6049. Min Act: -0.0000

Data Index: 1098512 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.4981. Min Act: -0.0000

Data Index: 1111412 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.5754. Min Act: -0.0000

Data Index: 1350800 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.4976. Min Act: -0.0000

Data Index: 817432 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.4821. Min Act: -0.0000

Data Index: 661456 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.4703. Min Act: -0.0000

Data Index: 254575 (C4 (Web Text))

Max Activating Token Index: 279