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

Dataset: The Pile

Neuron 3030 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: 1.5763. Min Range: -1.5763

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1128322 (The Pile)

Max Activating Token Index: 948

Text #1

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.4076. Min Act: -0.0000

Data Index: 242736 (The Pile)

Max Activating Token Index: 809

Text #2

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.5763. Min Act: -0.0000

Data Index: 213020 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.4656. Min Act: -0.0000

Data Index: 1869006 (The Pile)

Max Activating Token Index: 250

Text #4

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.3349. Min Act: -0.0000

Data Index: 16543 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.4742. Min Act: -0.0000

Data Index: 727004 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1106981 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1342465 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.2995. Min Act: -0.0000

Data Index: 765957 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.3091. Min Act: -0.0000

Data Index: 663809 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1153596 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.2267. Min Act: -0.0000

Data Index: 80655 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.1953. Min Act: -0.0000

Data Index: 878210 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.3457. Min Act: -0.0000

Data Index: 625393 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1044851 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1315603 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.3351. Min Act: -0.0000

Data Index: 340729 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1231904 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.1325. Min Act: -0.0000

Data Index: 1276426 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 1.5763. Min Range: -1.5763

Max Act: 1.2676. Min Act: -0.0000

Data Index: 440953 (The Pile)

Max Activating Token Index: 519