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

Dataset: The Pile

Neuron 1810 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.2608. Min Act: -0.0000

Data Index: 276740 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1632263 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.0927. Min Act: -0.0000

Data Index: 1285437 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1433036 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.8518. Min Act: -0.0000

Data Index: 813107 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.0429. Min Act: -0.0000

Data Index: 46638 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.1110. Min Act: -0.0000

Data Index: 959649 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1343144 (The Pile)

Max Activating Token Index: 782

Text #8

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.0109. Min Act: -0.0000

Data Index: 218963 (The Pile)

Max Activating Token Index: 467

Text #9

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9027. Min Act: -0.0000

Data Index: 403184 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9604. Min Act: -0.0000

Data Index: 249862 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9726. Min Act: -0.0000

Data Index: 499022 (The Pile)

Max Activating Token Index: 689

Text #12

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9086. Min Act: -0.0000

Data Index: 897312 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1079049 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9614. Min Act: -0.0000

Data Index: 357669 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1175027 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9584. Min Act: -0.0000

Data Index: 79594 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9457. Min Act: -0.0000

Data Index: 1526264 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9247. Min Act: -0.0000

Data Index: 537164 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9033. Min Act: -0.0000

Data Index: 145947 (The Pile)

Max Activating Token Index: 589