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

Dataset: The Pile

Neuron 4873 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: 3.6181. Min Range: -3.6181

Max Act: 3.6181. Min Act: -0.0000

Data Index: 404973 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 3.6181. Min Range: -3.6181

Max Act: 3.3408. Min Act: -0.0000

Data Index: 106864 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 3.6181. Min Range: -3.6181

Max Act: 3.1751. Min Act: -0.0000

Data Index: 869037 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 3.6181. Min Range: -3.6181

Max Act: 3.3374. Min Act: -0.0000

Data Index: 172157 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 3.6181. Min Range: -3.6181

Max Act: 3.3317. Min Act: -0.0000

Data Index: 835066 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 3.6181. Min Range: -3.6181

Max Act: 3.1379. Min Act: -0.0000

Data Index: 1141077 (The Pile)

Max Activating Token Index: 348

Text #6

Max Range: 3.6181. Min Range: -3.6181

Max Act: 3.0939. Min Act: -0.0000

Data Index: 364383 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 3.6181. Min Range: -3.6181

Max Act: 3.0770. Min Act: -0.0000

Data Index: 956747 (The Pile)

Max Activating Token Index: 607

Text #8

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.8484. Min Act: -0.0000

Data Index: 1764741 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.7538. Min Act: -0.0000

Data Index: 1044083 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.8811. Min Act: -0.0000

Data Index: 36010 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.9822. Min Act: -0.0000

Data Index: 211210 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.9522. Min Act: -0.0000

Data Index: 1706512 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.9435. Min Act: -0.0000

Data Index: 800345 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.9883. Min Act: -0.0000

Data Index: 705040 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.9205. Min Act: -0.0000

Data Index: 1322570 (The Pile)

Max Activating Token Index: 60

Text #16

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.7440. Min Act: -0.0000

Data Index: 1330598 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.7333. Min Act: -0.0000

Data Index: 1847802 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 3.6181. Min Range: -3.6181

Max Act: 3.0599. Min Act: -0.0000

Data Index: 1428999 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 3.6181. Min Range: -3.6181

Max Act: 2.6996. Min Act: -0.0000

Data Index: 1460126 (The Pile)

Max Activating Token Index: 651