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

Dataset: The Pile

Neuron 3738 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1714561 (The Pile)

Max Activating Token Index: 489

Text #1

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1207410 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1134548 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1834053 (The Pile)

Max Activating Token Index: 708

Text #4

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1960069 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4169. Min Act: -0.0000

Data Index: 611290 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1667624 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1464423 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1733333 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4104. Min Act: -0.0000

Data Index: 811806 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4196. Min Act: -0.0000

Data Index: 38631 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4365. Min Act: -0.0000

Data Index: 581959 (The Pile)

Max Activating Token Index: 360

Text #12

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1964826 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4147. Min Act: -0.0000

Data Index: 209428 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4134. Min Act: -0.0000

Data Index: 205211 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3851. Min Act: -0.0000

Data Index: 717879 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1177048 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3944. Min Act: -0.0000

Data Index: 770455 (The Pile)

Max Activating Token Index: 579

Text #18

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1845709 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3651. Min Act: -0.0000

Data Index: 634543 (The Pile)

Max Activating Token Index: 90