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

Dataset: The Pile

Neuron 252 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: 0.6190. Min Range: -0.6190

Max Act: 0.5922. Min Act: -0.0000

Data Index: 145050 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1321652 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5975. Min Act: -0.0000

Data Index: 246849 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1475775 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5325. Min Act: -0.0000

Data Index: 975540 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4843. Min Act: -0.0000

Data Index: 113482 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4932. Min Act: -0.0000

Data Index: 912566 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5369. Min Act: -0.0000

Data Index: 479097 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1906038 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5111. Min Act: -0.0000

Data Index: 885133 (The Pile)

Max Activating Token Index: 539

Text #10

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4804. Min Act: -0.0000

Data Index: 868612 (The Pile)

Max Activating Token Index: 947

Text #11

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1459159 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1214655 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5033. Min Act: -0.0000

Data Index: 403977 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4528. Min Act: -0.0000

Data Index: 860125 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4774. Min Act: -0.0000

Data Index: 428312 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1764484 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4278. Min Act: -0.0000

Data Index: 106461 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1839282 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4640. Min Act: -0.0000

Data Index: 804912 (The Pile)

Max Activating Token Index: 34