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

Dataset: The Pile

Neuron 3809 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: 4.2932. Min Range: -4.2932

Max Act: 4.2932. Min Act: -0.0000

Data Index: 754763 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 4.2932. Min Range: -4.2932

Max Act: 4.1168. Min Act: -0.0000

Data Index: 786321 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.7701. Min Act: -0.0000

Data Index: 1882400 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.7391. Min Act: -0.0000

Data Index: 1615681 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.4321. Min Act: -0.0000

Data Index: 851626 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.8792. Min Act: -0.0000

Data Index: 1065601 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.6919. Min Act: -0.0000

Data Index: 151228 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.5295. Min Act: -0.0000

Data Index: 500317 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.5920. Min Act: -0.0000

Data Index: 1910748 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.4157. Min Act: -0.0000

Data Index: 758176 (The Pile)

Max Activating Token Index: 451

Text #10

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.0683. Min Act: -0.0000

Data Index: 122373 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.2039. Min Act: -0.0000

Data Index: 258221 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.4459. Min Act: -0.0000

Data Index: 1574669 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.3217. Min Act: -0.0000

Data Index: 347027 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.1463. Min Act: -0.0000

Data Index: 476326 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.4477. Min Act: -0.0000

Data Index: 1488654 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.3892. Min Act: -0.0000

Data Index: 592026 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.3974. Min Act: -0.0000

Data Index: 450726 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.2501. Min Act: -0.0000

Data Index: 1647685 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 4.2932. Min Range: -4.2932

Max Act: 3.0753. Min Act: -0.0000

Data Index: 1936278 (The Pile)

Max Activating Token Index: 360