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

Dataset: The Pile

Neuron 3582 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: 0.4752. Min Range: -0.4752

Max Act: 0.4752. Min Act: -0.0000

Data Index: 275362 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1126819 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1813092 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3280. Min Act: -0.0000

Data Index: 528485 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1838738 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1309982 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1893151 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1031827 (The Pile)

Max Activating Token Index: 426

Text #8

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2444. Min Act: -0.0000

Data Index: 853434 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2453. Min Act: -0.0000

Data Index: 789714 (The Pile)

Max Activating Token Index: 544

Text #10

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1356652 (The Pile)

Max Activating Token Index: 933

Text #11

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2587. Min Act: -0.0000

Data Index: 116085 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1347444 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1491235 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1465633 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1261630 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2085. Min Act: -0.0000

Data Index: 149162 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1163201 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2018. Min Act: -0.0000

Data Index: 872338 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2101. Min Act: -0.0000

Data Index: 619100 (The Pile)

Max Activating Token Index: 913