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

Dataset: The Pile

Neuron 1658 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: 1.0132. Min Range: -1.0132

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1267905 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8283. Min Act: -0.0000

Data Index: 377396 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.9207. Min Act: -0.0000

Data Index: 135917 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1963423 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.9027. Min Act: -0.0000

Data Index: 147190 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1652660 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8998. Min Act: -0.0000

Data Index: 955365 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1244014 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1167011 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8439. Min Act: -0.0000

Data Index: 498459 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8645. Min Act: -0.0000

Data Index: 648979 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7938. Min Act: -0.0000

Data Index: 8613 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8083. Min Act: -0.0000

Data Index: 776806 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1442749 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8289. Min Act: -0.0001

Data Index: 498603 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8175. Min Act: -0.0000

Data Index: 936739 (The Pile)

Max Activating Token Index: 581

Text #16

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1368919 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1637794 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1512196 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1774725 (The Pile)

Max Activating Token Index: 231