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

Dataset: The Pile

Neuron 3545 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: 1.4196. Min Range: -1.4196

Max Act: 1.2833. Min Act: -0.0000

Data Index: 779157 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3345. Min Act: -0.0000

Data Index: 1989119 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.4196. Min Act: -0.0000

Data Index: 1107427 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1275. Min Act: -0.0000

Data Index: 1779691 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1293548 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.2083. Min Act: -0.0000

Data Index: 1573871 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.2314. Min Act: -0.0000

Data Index: 1422380 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.2301. Min Act: -0.0000

Data Index: 817716 (The Pile)

Max Activating Token Index: 533

Text #8

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1950583 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1117. Min Act: -0.0000

Data Index: 947824 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1666563 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1119. Min Act: -0.0000

Data Index: 195254 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1972898 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1465877 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1605465 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1194063 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1167079 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1838136 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0735. Min Act: -0.0000

Data Index: 442504 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0694. Min Act: -0.0000

Data Index: 816235 (The Pile)

Max Activating Token Index: 415