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

Dataset: The Pile

Neuron 1882 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: 0.8862. Min Range: -0.8862

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1087279 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6486. Min Act: -0.0000

Data Index: 887815 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1903240 (The Pile)

Max Activating Token Index: 871

Text #3

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6156. Min Act: -0.0000

Data Index: 825128 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1686820 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.4744. Min Act: -0.0000

Data Index: 865465 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5871. Min Act: -0.0000

Data Index: 119575 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1578782 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1843003 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1737877 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5606. Min Act: -0.0000

Data Index: 931746 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1226565 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1798832 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5258. Min Act: -0.0000

Data Index: 443659 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1286470 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1097221 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5842. Min Act: -0.0000

Data Index: 879645 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5231. Min Act: -0.0000

Data Index: 891545 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5179. Min Act: -0.0000

Data Index: 959428 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1196392 (The Pile)

Max Activating Token Index: 422