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

Dataset: The Pile

Neuron 1901 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: 1.6151. Min Range: -1.6151

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1459312 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.5872. Min Act: -0.0000

Data Index: 463719 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.6151. Min Act: -0.0000

Data Index: 657288 (The Pile)

Max Activating Token Index: 877

Text #3

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.4916. Min Act: -0.0000

Data Index: 1855353 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.4874. Min Act: -0.0000

Data Index: 207863 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1060949 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1539828 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1154509 (The Pile)

Max Activating Token Index: 614

Text #8

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.4150. Min Act: -0.0000

Data Index: 464263 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.3822. Min Act: -0.0000

Data Index: 191367 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1299247 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1365310 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.3442. Min Act: -0.0000

Data Index: 1395205 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1151841 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1301686 (The Pile)

Max Activating Token Index: 781

Text #15

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.2968. Min Act: -0.0000

Data Index: 91538 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1838838 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.1996. Min Act: -0.0000

Data Index: 579003 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.2927. Min Act: -0.0000

Data Index: 212321 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.4092. Min Act: -0.0000

Data Index: 1247640 (The Pile)

Max Activating Token Index: 756