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

Dataset: The Pile

Neuron 2574 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: 0.3926. Min Range: -0.3926

Max Act: 0.3926. Min Act: -0.0000

Data Index: 781002 (The Pile)

Max Activating Token Index: 409

Text #1

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3264. Min Act: -0.0000

Data Index: 722887 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1082824 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1663629 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1842005 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1436567 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2633. Min Act: -0.0000

Data Index: 75428 (The Pile)

Max Activating Token Index: 881

Text #7

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2523. Min Act: -0.0000

Data Index: 705168 (The Pile)

Max Activating Token Index: 342

Text #8

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1040453 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1879221 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1340746 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1683346 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2191. Min Act: -0.0000

Data Index: 541351 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2246. Min Act: -0.0000

Data Index: 862282 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1171541 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2206. Min Act: -0.0000

Data Index: 940670 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2075. Min Act: -0.0000

Data Index: 591362 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1864128 (The Pile)

Max Activating Token Index: 579

Text #18

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2260. Min Act: -0.0000

Data Index: 214935 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2278. Min Act: -0.0000

Data Index: 926149 (The Pile)

Max Activating Token Index: 797