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

Dataset: The Pile

Neuron 4854 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.2385. Min Act: -0.0000

Data Index: 597927 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1939913 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1475. Min Act: -0.0000

Data Index: 1852390 (The Pile)

Max Activating Token Index: 508

Text #3

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1236970 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1079. Min Act: -0.0000

Data Index: 179097 (The Pile)

Max Activating Token Index: 408

Text #5

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1225500 (The Pile)

Max Activating Token Index: 730

Text #6

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1969994 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1961583 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1631396 (The Pile)

Max Activating Token Index: 576

Text #9

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1989494 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0345. Min Act: -0.0000

Data Index: 499902 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0228. Min Act: -0.0000

Data Index: 73073 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0750. Min Act: -0.0000

Data Index: 470531 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0103. Min Act: -0.0000

Data Index: 91912 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1757286 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1492439 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0151. Min Act: -0.0000

Data Index: 242063 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0278. Min Act: -0.0000

Data Index: 948745 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0137. Min Act: -0.0000

Data Index: 510598 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9324. Min Act: -0.0000

Data Index: 139943 (The Pile)

Max Activating Token Index: 927