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

Dataset: The Pile

Neuron 3094 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: 0.6271. Min Range: -0.6271

Max Act: 0.6271. Min Act: -0.0000

Data Index: 77480 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5092. Min Act: -0.0000

Data Index: 284675 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4160. Min Act: -0.0000

Data Index: 797539 (The Pile)

Max Activating Token Index: 954

Text #3

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4506. Min Act: -0.0000

Data Index: 848935 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1060121 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1407446 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1335310 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4725. Min Act: -0.0000

Data Index: 238545 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1316061 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1637384 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4042. Min Act: -0.0000

Data Index: 209897 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4442. Min Act: -0.0000

Data Index: 940578 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1200426 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1247601 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4044. Min Act: -0.0000

Data Index: 61646 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1904967 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.3942. Min Act: -0.0000

Data Index: 596425 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.3778. Min Act: -0.0000

Data Index: 463063 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4040. Min Act: -0.0000

Data Index: 407887 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1845284 (The Pile)

Max Activating Token Index: 803