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

Dataset: The Pile

Neuron 3885 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.8238. Min Act: -0.0000

Data Index: 693533 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.4730. Min Act: -0.0000

Data Index: 1656326 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.5269. Min Act: -0.0000

Data Index: 53724 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.3997. Min Act: -0.0000

Data Index: 1273020 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.7870. Min Act: -0.0000

Data Index: 1728591 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.0575. Min Act: -0.0000

Data Index: 272674 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.4394. Min Act: -0.0000

Data Index: 1679316 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.4029. Min Act: -0.0000

Data Index: 464105 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.3464. Min Act: -0.0000

Data Index: 472664 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1183042 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.2241. Min Act: -0.0000

Data Index: 160888 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1271657 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.4272. Min Act: -0.0000

Data Index: 1941985 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.1989. Min Act: -0.0000

Data Index: 798874 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.6503. Min Act: -0.0000

Data Index: 300472 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1927060 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.3018. Min Act: -0.0000

Data Index: 499198 (The Pile)

Max Activating Token Index: 451

Text #17

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1049333 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.3025. Min Act: -0.0000

Data Index: 1649961 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 1.8238. Min Range: -1.8238

Max Act: 1.2930. Min Act: -0.0000

Data Index: 103746 (The Pile)

Max Activating Token Index: 480