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

Dataset: The Pile

Neuron 1007 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1020020 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3794. Min Act: -0.0000

Data Index: 263931 (The Pile)

Max Activating Token Index: 222

Text #2

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3603. Min Act: -0.0000

Data Index: 278640 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1878721 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1275593 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3469. Min Act: -0.0000

Data Index: 360796 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3218. Min Act: -0.0000

Data Index: 562750 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3853. Min Act: -0.0000

Data Index: 578518 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1956163 (The Pile)

Max Activating Token Index: 768

Text #9

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3480. Min Act: -0.0000

Data Index: 680993 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3053. Min Act: -0.0000

Data Index: 296791 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1153911 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3544. Min Act: -0.0000

Data Index: 26845 (The Pile)

Max Activating Token Index: 985

Text #13

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2787. Min Act: -0.0000

Data Index: 586776 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1385233 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1695844 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3072. Min Act: -0.0000

Data Index: 725327 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3007. Min Act: -0.0000

Data Index: 606874 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1028274 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1368328 (The Pile)

Max Activating Token Index: 397