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

Dataset: The Pile

Neuron 3109 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7544. Min Act: -0.0000

Data Index: 148310 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7594. Min Act: -0.0000

Data Index: 225561 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7524. Min Act: -0.0000

Data Index: 815811 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6979. Min Act: -0.0000

Data Index: 744387 (The Pile)

Max Activating Token Index: 379

Text #4

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1748583 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6656. Min Act: -0.0000

Data Index: 10200 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1617293 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6367. Min Act: -0.0000

Data Index: 194630 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1879253 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6180. Min Act: -0.0000

Data Index: 559436 (The Pile)

Max Activating Token Index: 655

Text #10

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1210864 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1138537 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1043446 (The Pile)

Max Activating Token Index: 620

Text #13

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1326794 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6325. Min Act: -0.0000

Data Index: 412437 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1923613 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1169911 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1260324 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1061833 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1329995 (The Pile)

Max Activating Token Index: 739