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

Dataset: The Pile

Neuron 1962 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6955. Min Range: -6.6955

Max Act: 6.5213. Min Act: -0.0000

Data Index: 1423566 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.7862. Min Act: -0.0000

Data Index: 708684 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.8795. Min Act: -0.0000

Data Index: 1098327 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 6.6955. Min Range: -6.6955

Max Act: 6.1176. Min Act: -0.0000

Data Index: 317171 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 6.6955. Min Range: -6.6955

Max Act: 6.4086. Min Act: -0.0000

Data Index: 1670324 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.7048. Min Act: -0.0000

Data Index: 1205185 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.2990. Min Act: -0.0000

Data Index: 709317 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 6.6955. Min Range: -6.6955

Max Act: 6.6955. Min Act: -0.0000

Data Index: 239076 (The Pile)

Max Activating Token Index: 514

Text #8

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.5895. Min Act: -0.0000

Data Index: 1107486 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.3036. Min Act: -0.0000

Data Index: 1984345 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 6.6955. Min Range: -6.6955

Max Act: 6.4474. Min Act: -0.0000

Data Index: 1428498 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.7988. Min Act: -0.0000

Data Index: 954066 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.6389. Min Act: -0.0000

Data Index: 1484654 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 6.6955. Min Range: -6.6955

Max Act: 6.0163. Min Act: -0.0000

Data Index: 1115375 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.4820. Min Act: -0.0000

Data Index: 1602979 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.0991. Min Act: -0.0000

Data Index: 890165 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.2710. Min Act: -0.0000

Data Index: 1414014 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.6989. Min Act: -0.0000

Data Index: 909154 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.6858. Min Act: -0.0000

Data Index: 1394476 (The Pile)

Max Activating Token Index: 536

Text #19

Max Range: 6.6955. Min Range: -6.6955

Max Act: 5.8126. Min Act: -0.0000

Data Index: 739111 (The Pile)

Max Activating Token Index: 226