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

Dataset: The Pile

Neuron 2022 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: 1.2437. Min Range: -1.2437

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1558123 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 1.2437. Min Range: -1.2437

Max Act: 1.0801. Min Act: -0.0000

Data Index: 156958 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1647244 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 1.2437. Min Range: -1.2437

Max Act: 1.0116. Min Act: -0.0000

Data Index: 673354 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 1.2437. Min Range: -1.2437

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1827570 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1734912 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8804. Min Act: -0.0000

Data Index: 658944 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1172771 (The Pile)

Max Activating Token Index: 777

Text #8

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8374. Min Act: -0.0000

Data Index: 518425 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1842708 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8458. Min Act: -0.0000

Data Index: 931532 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.7562. Min Act: -0.0001

Data Index: 1881029 (The Pile)

Max Activating Token Index: 424

Text #12

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.7928. Min Act: -0.0000

Data Index: 579191 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1461320 (The Pile)

Max Activating Token Index: 507

Text #14

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.7461. Min Act: -0.0000

Data Index: 632696 (The Pile)

Max Activating Token Index: 850

Text #15

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1957427 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1323169 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1460380 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.7794. Min Act: -0.0000

Data Index: 649079 (The Pile)

Max Activating Token Index: 426

Text #19

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1141179 (The Pile)

Max Activating Token Index: 827