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

Dataset: The Pile

Neuron 1273 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: 0.3721. Min Range: -0.3721

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1349831 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3223. Min Act: -0.0000

Data Index: 265990 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1397250 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1891825 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2996. Min Act: -0.0000

Data Index: 280817 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2809. Min Act: -0.0000

Data Index: 463198 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1144780 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1332836 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2858. Min Act: -0.0000

Data Index: 922875 (The Pile)

Max Activating Token Index: 602

Text #9

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1496527 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1917102 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1292658 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2304. Min Act: -0.0000

Data Index: 671229 (The Pile)

Max Activating Token Index: 841

Text #13

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1134441 (The Pile)

Max Activating Token Index: 353

Text #14

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2397. Min Act: -0.0000

Data Index: 325178 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1921771 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1385480 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2676. Min Act: -0.0000

Data Index: 576347 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1428164 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2333. Min Act: -0.0000

Data Index: 282155 (The Pile)

Max Activating Token Index: 384