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

Dataset: The Pile

Neuron 399 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: 1.4770. Min Range: -1.4770

Max Act: 1.4770. Min Act: -0.0000

Data Index: 1128264 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.4161. Min Act: -0.0000

Data Index: 1158179 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1528070 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3608. Min Act: -0.0000

Data Index: 1726943 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3960. Min Act: -0.0000

Data Index: 566546 (The Pile)

Max Activating Token Index: 367

Text #5

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1277979 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2743. Min Act: -0.0000

Data Index: 1738768 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1518871 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2359. Min Act: -0.0000

Data Index: 1547084 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1588388 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1735808 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3680. Min Act: -0.0000

Data Index: 328923 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3615. Min Act: -0.0000

Data Index: 343207 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1177357 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3003. Min Act: -0.0000

Data Index: 1120697 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3348. Min Act: -0.0000

Data Index: 1236303 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1390470 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2953. Min Act: -0.0000

Data Index: 647474 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3260. Min Act: -0.0000

Data Index: 806737 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2223. Min Act: -0.0000

Data Index: 1387003 (The Pile)

Max Activating Token Index: 4