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

Dataset: The Pile

Neuron 2737 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: 0.4394. Min Range: -0.4394

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1088257 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4227. Min Act: -0.0000

Data Index: 816852 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3873. Min Act: -0.0000

Data Index: 929940 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1735645 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1714258 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1515917 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1441134 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1256910 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1746670 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1030530 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1755376 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1622350 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2620. Min Act: -0.0000

Data Index: 163288 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1635633 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3029. Min Act: -0.0000

Data Index: 5341 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2916. Min Act: -0.0000

Data Index: 429534 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1742113 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2840. Min Act: -0.0000

Data Index: 237165 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1096448 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2794. Min Act: -0.0000

Data Index: 640601 (The Pile)

Max Activating Token Index: 852