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

Dataset: The Pile

Neuron 3373 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: 1.5021. Min Range: -1.5021

Max Act: 1.5021. Min Act: -0.0000

Data Index: 1398995 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.4519. Min Act: -0.0000

Data Index: 553161 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.4326. Min Act: -0.0000

Data Index: 899915 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.4233. Min Act: -0.0000

Data Index: 113388 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.4221. Min Act: -0.0000

Data Index: 146839 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1574953 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1853048 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1250447 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1974. Min Act: -0.0000

Data Index: 401069 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.2500. Min Act: -0.0000

Data Index: 939418 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1736. Min Act: -0.0000

Data Index: 1293496 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1956. Min Act: -0.0000

Data Index: 746330 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1230667 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1729360 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1495. Min Act: -0.0000

Data Index: 468630 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1158949 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1653685 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.0041. Min Act: -0.0000

Data Index: 91500 (The Pile)

Max Activating Token Index: 534

Text #18

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1413. Min Act: -0.0000

Data Index: 1940222 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1180. Min Act: -0.0000

Data Index: 231321 (The Pile)

Max Activating Token Index: 30