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

Dataset: The Pile

Neuron 3170 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: 0.3134. Min Range: -0.3134

Max Act: 0.3134. Min Act: -0.0000

Data Index: 553951 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2831. Min Act: -0.0000

Data Index: 659313 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2818. Min Act: -0.0000

Data Index: 25435 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1362730 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1601419 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2257. Min Act: -0.0000

Data Index: 809870 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1405221 (The Pile)

Max Activating Token Index: 676

Text #7

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1521129 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2266. Min Act: -0.0000

Data Index: 604880 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2349. Min Act: -0.0000

Data Index: 890252 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1341846 (The Pile)

Max Activating Token Index: 688

Text #11

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2149. Min Act: -0.0000

Data Index: 728476 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1486820 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1415140 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1055091 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1924. Min Act: -0.0000

Data Index: 958791 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2121. Min Act: -0.0000

Data Index: 227573 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1007570 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1965. Min Act: -0.0000

Data Index: 514388 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1384823 (The Pile)

Max Activating Token Index: 963