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

Dataset: The Pile

Neuron 88 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: 7.1463. Min Range: -7.1463

Max Act: 6.9860. Min Act: -0.0000

Data Index: 426650 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 7.1463. Min Range: -7.1463

Max Act: 7.1463. Min Act: -0.0000

Data Index: 1274277 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 7.1463. Min Range: -7.1463

Max Act: 6.9266. Min Act: -0.0000

Data Index: 1441441 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.6534. Min Act: -0.0000

Data Index: 1122561 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.5760. Min Act: -0.0000

Data Index: 1540088 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.7543. Min Act: -0.0000

Data Index: 451409 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.6094. Min Act: -0.0000

Data Index: 879601 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.3951. Min Act: -0.0000

Data Index: 18945 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.6093. Min Act: -0.0000

Data Index: 1476971 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.5013. Min Act: -0.0000

Data Index: 631772 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.0472. Min Act: -0.0000

Data Index: 223777 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.2593. Min Act: -0.0000

Data Index: 55483 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.7575. Min Act: -0.0000

Data Index: 1859764 (The Pile)

Max Activating Token Index: 853

Text #13

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.3536. Min Act: -0.0000

Data Index: 1430326 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 7.1463. Min Range: -7.1463

Max Act: 4.7706. Min Act: -0.0000

Data Index: 1025581 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.0354. Min Act: -0.0000

Data Index: 177216 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.1943. Min Act: -0.0000

Data Index: 1256833 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 7.1463. Min Range: -7.1463

Max Act: 5.1432. Min Act: -0.0000

Data Index: 56853 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 7.1463. Min Range: -7.1463

Max Act: 4.9879. Min Act: -0.0000

Data Index: 868565 (The Pile)

Max Activating Token Index: 587

Text #19

Max Range: 7.1463. Min Range: -7.1463

Max Act: 4.9086. Min Act: -0.0000

Data Index: 361909 (The Pile)

Max Activating Token Index: 761