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

Dataset: The Pile

Neuron 2351 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.3104. Min Act: -0.0000

Data Index: 1985201 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.1741. Min Act: -0.0000

Data Index: 141822 (The Pile)

Max Activating Token Index: 691

Text #2

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0704. Min Act: -0.0000

Data Index: 1020565 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.2188. Min Act: -0.0000

Data Index: 1522440 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.8153. Min Act: -0.0000

Data Index: 398785 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.7462. Min Act: -0.0000

Data Index: 845567 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.7222. Min Act: -0.0000

Data Index: 1125669 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.9947. Min Act: -0.0000

Data Index: 1741983 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.8381. Min Act: -0.0000

Data Index: 630503 (The Pile)

Max Activating Token Index: 2

Text #9

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.8381. Min Act: -0.0000

Data Index: 1306814 (The Pile)

Max Activating Token Index: 2

Text #10

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.8010. Min Act: -0.0000

Data Index: 1290529 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.8960. Min Act: -0.0000

Data Index: 63171 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.5835. Min Act: -0.0000

Data Index: 1283411 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.5584. Min Act: -0.0000

Data Index: 537459 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.6811. Min Act: -0.0000

Data Index: 1587867 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.5239. Min Act: -0.0000

Data Index: 1365592 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.6597. Min Act: -0.0000

Data Index: 236167 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.5344. Min Act: -0.0000

Data Index: 531860 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.6477. Min Act: -0.0000

Data Index: 585704 (The Pile)

Max Activating Token Index: 720

Text #19

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.6380. Min Act: -0.0000

Data Index: 850374 (The Pile)

Max Activating Token Index: 453