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

Dataset: The Pile

Neuron 799 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: 1.4522. Min Range: -1.4522

Max Act: 1.4522. Min Act: -0.0000

Data Index: 945655 (The Pile)

Max Activating Token Index: 588

Text #1

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1326920 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.9842. Min Act: -0.0000

Data Index: 856452 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.7981. Min Act: -0.0000

Data Index: 175474 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1786804 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1826441 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.6067. Min Act: -0.0000

Data Index: 848818 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.7052. Min Act: -0.0000

Data Index: 607510 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.6646. Min Act: -0.0000

Data Index: 558542 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.6493. Min Act: -0.0000

Data Index: 361008 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1913879 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.5826. Min Act: -0.0000

Data Index: 981783 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1679772 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1692178 (The Pile)

Max Activating Token Index: 667

Text #14

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.5289. Min Act: -0.0000

Data Index: 922532 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.5493. Min Act: -0.0000

Data Index: 100059 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1065051 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1048021 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1006376 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 1.4522. Min Range: -1.4522

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1027900 (The Pile)

Max Activating Token Index: 40