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

Dataset: The Pile

Neuron 2254 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.8620. Min Act: -0.0000

Data Index: 1126076 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.5819. Min Act: -0.0000

Data Index: 1625616 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.5436. Min Act: -0.0000

Data Index: 546095 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.5016. Min Act: -0.0000

Data Index: 294849 (The Pile)

Max Activating Token Index: 303

Text #4

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.4843. Min Act: -0.0000

Data Index: 1878547 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.4223. Min Act: -0.0000

Data Index: 144654 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.3947. Min Act: -0.0000

Data Index: 1177377 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.5253. Min Act: -0.0000

Data Index: 150143 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.3710. Min Act: -0.0000

Data Index: 973080 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.2440. Min Act: -0.0000

Data Index: 1903908 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.0870. Min Act: -0.0000

Data Index: 1656253 (The Pile)

Max Activating Token Index: 914

Text #11

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.2057. Min Act: -0.0000

Data Index: 1309905 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.0405. Min Act: -0.0000

Data Index: 359853 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.1754. Min Act: -0.0000

Data Index: 998620 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.3037. Min Act: -0.0000

Data Index: 1092310 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.2603. Min Act: -0.0000

Data Index: 1373690 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 3.8620. Min Range: -3.8620

Max Act: 2.9631. Min Act: -0.0000

Data Index: 1856883 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.2365. Min Act: -0.0000

Data Index: 1831381 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 3.8620. Min Range: -3.8620

Max Act: 2.9344. Min Act: -0.0000

Data Index: 1855930 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 3.8620. Min Range: -3.8620

Max Act: 3.0368. Min Act: -0.0000

Data Index: 152212 (The Pile)

Max Activating Token Index: 712