Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 425 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1932198 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4534. Min Act: -0.0000

Data Index: 532729 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1637001 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4455. Min Act: -0.0000

Data Index: 340938 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1877386 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4166. Min Act: -0.0000

Data Index: 653358 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1388148 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3666. Min Act: -0.0000

Data Index: 84128 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3866. Min Act: -0.0000

Data Index: 690773 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1321729 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3994. Min Act: -0.0000

Data Index: 211160 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3375. Min Act: -0.0000

Data Index: 307621 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3576. Min Act: -0.0000

Data Index: 913826 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3487. Min Act: -0.0000

Data Index: 340096 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1305573 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3850. Min Act: -0.0000

Data Index: 111374 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3497. Min Act: -0.0000

Data Index: 616622 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3905. Min Act: -0.0000

Data Index: 315168 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1402488 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1654924 (The Pile)

Max Activating Token Index: 704