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

Dataset: The Pile

Neuron 1153 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: 10.1461. Min Range: -10.1461

Max Act: 9.8050. Min Act: -0.0000

Data Index: 1617191 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.9317. Min Act: -0.0000

Data Index: 1920024 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.6221. Min Act: -0.0000

Data Index: 1038644 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.4208. Min Act: -0.0000

Data Index: 569967 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 10.1461. Min Range: -10.1461

Max Act: 10.1461. Min Act: -0.0000

Data Index: 1392205 (The Pile)

Max Activating Token Index: 711

Text #5

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.1358. Min Act: -0.0000

Data Index: 1027456 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.3063. Min Act: -0.0000

Data Index: 786307 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.1737. Min Act: -0.0000

Data Index: 44539 (The Pile)

Max Activating Token Index: 35

Text #8

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.2693. Min Act: -0.0000

Data Index: 1742880 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.2169. Min Act: -0.0000

Data Index: 1709055 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.3893. Min Act: -0.0000

Data Index: 370791 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.0263. Min Act: -0.0000

Data Index: 1370923 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.2071. Min Act: -0.0000

Data Index: 885578 (The Pile)

Max Activating Token Index: 957

Text #13

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.1504. Min Act: -0.0000

Data Index: 989876 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.6450. Min Act: -0.0000

Data Index: 55279 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.6063. Min Act: -0.0000

Data Index: 285336 (The Pile)

Max Activating Token Index: 453

Text #16

Max Range: 10.1461. Min Range: -10.1461

Max Act: 8.9075. Min Act: -0.0000

Data Index: 1386275 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.0449. Min Act: -0.0000

Data Index: 1586839 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.2483. Min Act: -0.0000

Data Index: 723046 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 10.1461. Min Range: -10.1461

Max Act: 9.3609. Min Act: -0.0000

Data Index: 1335064 (The Pile)

Max Activating Token Index: 828