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

Dataset: The Pile

Neuron 2162 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: 1.2244. Min Range: -1.2244

Max Act: 1.2211. Min Act: -0.0000

Data Index: 223595 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.1928. Min Act: -0.0000

Data Index: 884874 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.2244. Min Act: -0.0000

Data Index: 1408720 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0896. Min Act: -0.0000

Data Index: 642091 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1326100 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.1140. Min Act: -0.0000

Data Index: 804140 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.1033. Min Act: -0.0000

Data Index: 839872 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.1220. Min Act: -0.0000

Data Index: 1615892 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0809. Min Act: -0.0000

Data Index: 583622 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1881756 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0903. Min Act: -0.0000

Data Index: 70301 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1283196 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1482959 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0271. Min Act: -0.0000

Data Index: 692361 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1869578 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.9954. Min Act: -0.0000

Data Index: 371801 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0630. Min Act: -0.0000

Data Index: 1356832 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0292. Min Act: -0.0000

Data Index: 663728 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1671516 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0113. Min Act: -0.0000

Data Index: 266140 (The Pile)

Max Activating Token Index: 681