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

Dataset: The Pile

Neuron 3424 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3881. Min Range: -1.3881

Max Act: 1.3881. Min Act: -0.0000

Data Index: 806322 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 1.3881. Min Range: -1.3881

Max Act: 1.1022. Min Act: -0.0000

Data Index: 236596 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 1.3881. Min Range: -1.3881

Max Act: 1.0519. Min Act: -0.0000

Data Index: 521920 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 1.3881. Min Range: -1.3881

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1885607 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.9716. Min Act: -0.0000

Data Index: 191998 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1566071 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 1.3881. Min Range: -1.3881

Max Act: 1.0238. Min Act: -0.0000

Data Index: 711872 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 1.3881. Min Range: -1.3881

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1191883 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.9914. Min Act: -0.0000

Data Index: 555027 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1650499 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1437614 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1497162 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1119203 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1864244 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1299326 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1444735 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1489605 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1164344 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1779887 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8663. Min Act: -0.0000

Data Index: 777032 (The Pile)

Max Activating Token Index: 769