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

Dataset: The Pile

Neuron 4827 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: 0.5994. Min Range: -0.5994

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1491256 (The Pile)

Max Activating Token Index: 313

Text #1

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1243861 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1873543 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4509. Min Act: -0.0000

Data Index: 25249 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1197335 (The Pile)

Max Activating Token Index: 290

Text #5

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1054742 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1342773 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1986114 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3772. Min Act: -0.0000

Data Index: 323561 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1164615 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3277. Min Act: -0.0000

Data Index: 115320 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1282658 (The Pile)

Max Activating Token Index: 476

Text #12

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.2922. Min Act: -0.0000

Data Index: 86968 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3112. Min Act: -0.0000

Data Index: 108685 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.2955. Min Act: -0.0000

Data Index: 333354 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1744592 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1332849 (The Pile)

Max Activating Token Index: 940

Text #17

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1892980 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3195. Min Act: -0.0000

Data Index: 778981 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1931102 (The Pile)

Max Activating Token Index: 524