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

Dataset: The Pile

Neuron 2711 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1620107 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1078775 (The Pile)

Max Activating Token Index: 630

Text #2

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4192. Min Act: -0.0000

Data Index: 487817 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1739751 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3910. Min Act: -0.0000

Data Index: 906316 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1139671 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1239412 (The Pile)

Max Activating Token Index: 538

Text #7

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1290746 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3711. Min Act: -0.0000

Data Index: 376071 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3394. Min Act: 0.0000

Data Index: 269774 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3524. Min Act: -0.0000

Data Index: 747125 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1598811 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1443342 (The Pile)

Max Activating Token Index: 378

Text #13

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3519. Min Act: -0.0000

Data Index: 123400 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3413. Min Act: 0.0000

Data Index: 188261 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1647605 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3481. Min Act: 0.0002

Data Index: 1790446 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3592. Min Act: -0.0000

Data Index: 809140 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3544. Min Act: 0.0000

Data Index: 1889094 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.3309. Min Act: -0.0000

Data Index: 732031 (The Pile)

Max Activating Token Index: 917