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

Dataset: The Pile

Neuron 2030 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1622. Min Range: -1.1622

Max Act: 1.1622. Min Act: -0.0000

Data Index: 122438 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1036945 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.7257. Min Act: -0.0000

Data Index: 760417 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1159147 (The Pile)

Max Activating Token Index: 748

Text #4

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.5385. Min Act: -0.0000

Data Index: 246552 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.5312. Min Act: -0.0000

Data Index: 537986 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.5051. Min Act: -0.0000

Data Index: 99379 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1435278 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.5758. Min Act: -0.0000

Data Index: 497575 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.4927. Min Act: -0.0000

Data Index: 554077 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.5324. Min Act: -0.0000

Data Index: 92125 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.6006. Min Act: -0.0000

Data Index: 473353 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1268218 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1837159 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.4832. Min Act: -0.0000

Data Index: 675190 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.4262. Min Act: -0.0000

Data Index: 914153 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1605273 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.4453. Min Act: -0.0000

Data Index: 369499 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.3939. Min Act: -0.0000

Data Index: 500045 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.4414. Min Act: -0.0000

Data Index: 588245 (The Pile)

Max Activating Token Index: 28