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

Dataset: The Pile

Neuron 4902 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.5814. Min Act: -0.0000

Data Index: 724405 (The Pile)

Max Activating Token Index: 225

Text #1

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.6034. Min Act: -0.0000

Data Index: 519224 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.5421. Min Act: -0.0000

Data Index: 864294 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1264299 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4431. Min Act: -0.0000

Data Index: 699653 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1431082 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.5086. Min Act: -0.0000

Data Index: 527445 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4564. Min Act: -0.0000

Data Index: 234623 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1552491 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1002952 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4423. Min Act: -0.0000

Data Index: 771637 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1089528 (The Pile)

Max Activating Token Index: 650

Text #12

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1289910 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1302137 (The Pile)

Max Activating Token Index: 947

Text #14

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4356. Min Act: -0.0000

Data Index: 342583 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4247. Min Act: -0.0000

Data Index: 205130 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4760. Min Act: -0.0000

Data Index: 66521 (The Pile)

Max Activating Token Index: 504

Text #17

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4243. Min Act: -0.0000

Data Index: 265549 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4577. Min Act: -0.0000

Data Index: 47285 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1563787 (The Pile)

Max Activating Token Index: 754