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

Dataset: The Pile

Neuron 1297 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1327725 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3350. Min Act: -0.0000

Data Index: 482319 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1678857 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1833206 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3204. Min Act: -0.0000

Data Index: 510184 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1145325 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1851155 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1579177 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1799942 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1197987 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2887. Min Act: -0.0000

Data Index: 160671 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1601564 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1169682 (The Pile)

Max Activating Token Index: 652

Text #13

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2955. Min Act: -0.0000

Data Index: 762347 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2842. Min Act: -0.0000

Data Index: 144196 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1784413 (The Pile)

Max Activating Token Index: 567

Text #16

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1261436 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2776. Min Act: -0.0000

Data Index: 663164 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1019157 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1072408 (The Pile)

Max Activating Token Index: 1012