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

Dataset: The Pile

Neuron 3399 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: 0.8961. Min Range: -0.8961

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1464096 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8560. Min Act: -0.0000

Data Index: 12638 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1110937 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7829. Min Act: -0.0000

Data Index: 152574 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7241. Min Act: -0.0000

Data Index: 274109 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7173. Min Act: -0.0000

Data Index: 716484 (The Pile)

Max Activating Token Index: 149

Text #6

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1539532 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1297464 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1254614 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7085. Min Act: -0.0000

Data Index: 317653 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7384. Min Act: -0.0000

Data Index: 649451 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1717852 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7361. Min Act: -0.0000

Data Index: 462038 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1770119 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6732. Min Act: -0.0000

Data Index: 491500 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7628. Min Act: -0.0000

Data Index: 790822 (The Pile)

Max Activating Token Index: 977

Text #16

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6714. Min Act: -0.0000

Data Index: 189289 (The Pile)

Max Activating Token Index: 889

Text #17

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6392. Min Act: -0.0000

Data Index: 224010 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1513032 (The Pile)

Max Activating Token Index: 823

Text #19

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6902. Min Act: -0.0000

Data Index: 484866 (The Pile)

Max Activating Token Index: 603