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

Dataset: The Pile

Neuron 447 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1136080 (The Pile)

Max Activating Token Index: 371

Text #1

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1545530 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5240. Min Act: -0.0000

Data Index: 736356 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4871. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1891421 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4970. Min Act: -0.0000

Data Index: 798410 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1399521 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1082601 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4701. Min Act: -0.0000

Data Index: 808259 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5713. Min Act: -0.0000

Data Index: 5043 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4220. Min Act: -0.0000

Data Index: 356844 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4862. Min Act: -0.0000

Data Index: 315384 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4400. Min Act: -0.0000

Data Index: 303353 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1358998 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1094184 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1183817 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1829108 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1211738 (The Pile)

Max Activating Token Index: 624

Text #18

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1137097 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1588127 (The Pile)

Max Activating Token Index: 289