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

Dataset: The Pile

Neuron 220 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: 0.3734. Min Range: -0.3734

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1810059 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2920. Min Act: -0.0000

Data Index: 164306 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2715. Min Act: -0.0000

Data Index: 380350 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1989120 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1125250 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1091497 (The Pile)

Max Activating Token Index: 458

Text #6

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2466. Min Act: -0.0000

Data Index: 433259 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1033092 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2318. Min Act: -0.0000

Data Index: 51114 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2257. Min Act: -0.0000

Data Index: 253764 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2196. Min Act: -0.0000

Data Index: 89164 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2197. Min Act: -0.0000

Data Index: 487802 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1008140 (The Pile)

Max Activating Token Index: 666

Text #13

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2137. Min Act: -0.0000

Data Index: 869090 (The Pile)

Max Activating Token Index: 814

Text #14

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2249. Min Act: -0.0000

Data Index: 56999 (The Pile)

Max Activating Token Index: 658

Text #15

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1163811 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2208. Min Act: -0.0000

Data Index: 435939 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1471097 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1379165 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1968406 (The Pile)

Max Activating Token Index: 297