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

Dataset: The Pile

Neuron 2261 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9230. Min Act: -0.0000

Data Index: 323067 (The Pile)

Max Activating Token Index: 232

Text #1

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0768. Min Act: -0.0000

Data Index: 119246 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1473633 (The Pile)

Max Activating Token Index: 153

Text #3

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1501116 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8593. Min Act: -0.0000

Data Index: 116660 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8499. Min Act: -0.0000

Data Index: 623693 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8057. Min Act: -0.0000

Data Index: 610147 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8828. Min Act: -0.0000

Data Index: 679856 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7109. Min Act: -0.0000

Data Index: 889618 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1355093 (The Pile)

Max Activating Token Index: 457

Text #10

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8044. Min Act: -0.0000

Data Index: 821124 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7495. Min Act: -0.0000

Data Index: 102292 (The Pile)

Max Activating Token Index: 404

Text #12

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7029. Min Act: -0.0000

Data Index: 623290 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7378. Min Act: -0.0000

Data Index: 466892 (The Pile)

Max Activating Token Index: 381

Text #14

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1578865 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7911. Min Act: -0.0000

Data Index: 679071 (The Pile)

Max Activating Token Index: 700

Text #16

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7988. Min Act: -0.0000

Data Index: 417956 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1597467 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1570864 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1654460 (The Pile)

Max Activating Token Index: 509