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

Dataset: The Pile

Neuron 1567 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 14.3271. Min Range: -14.3271

Max Act: 14.3271. Min Act: -0.0000

Data Index: 953748 (The Pile)

Max Activating Token Index: 62

Text #1

Max Range: 14.3271. Min Range: -14.3271

Max Act: 14.1942. Min Act: -0.0000

Data Index: 1235103 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 14.3271. Min Range: -14.3271

Max Act: 14.0968. Min Act: -0.0000

Data Index: 397058 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 14.3271. Min Range: -14.3271

Max Act: 14.0402. Min Act: -0.0000

Data Index: 312927 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.8897. Min Act: -0.0000

Data Index: 1923950 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.9741. Min Act: -0.0000

Data Index: 700857 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.8981. Min Act: -0.0000

Data Index: 131535 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 14.3271. Min Range: -14.3271

Max Act: 14.0459. Min Act: -0.0000

Data Index: 358215 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.8350. Min Act: -0.0000

Data Index: 475235 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 14.3271. Min Range: -14.3271

Max Act: 14.0402. Min Act: -0.0000

Data Index: 982078 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.8177. Min Act: -0.0000

Data Index: 1337840 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.7349. Min Act: -0.0000

Data Index: 1418219 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.7698. Min Act: -0.0000

Data Index: 1285480 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.6082. Min Act: -0.0000

Data Index: 1443873 (The Pile)

Max Activating Token Index: 202

Text #14

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.6113. Min Act: -0.0000

Data Index: 853974 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.5182. Min Act: -0.0000

Data Index: 712985 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.6894. Min Act: -0.0000

Data Index: 853952 (The Pile)

Max Activating Token Index: 200

Text #17

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.3861. Min Act: -0.0000

Data Index: 1333855 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.3692. Min Act: -0.0000

Data Index: 1565519 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 14.3271. Min Range: -14.3271

Max Act: 13.4479. Min Act: -0.0000

Data Index: 686829 (The Pile)

Max Activating Token Index: 465