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

Dataset: The Pile

Neuron 1280 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: 0.4697. Min Range: -0.4697

Max Act: 0.4697. Min Act: -0.0000

Data Index: 212243 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4253. Min Act: -0.0000

Data Index: 912748 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1178555 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3996. Min Act: -0.0000

Data Index: 171318 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1859669 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3591. Min Act: -0.0000

Data Index: 935084 (The Pile)

Max Activating Token Index: 845

Text #6

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3314. Min Act: -0.0000

Data Index: 13703 (The Pile)

Max Activating Token Index: 933

Text #7

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1262798 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3688. Min Act: -0.0000

Data Index: 492113 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3332. Min Act: -0.0000

Data Index: 1242349 (The Pile)

Max Activating Token Index: 860

Text #10

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3530. Min Act: -0.0000

Data Index: 486066 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1145337 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3224. Min Act: -0.0000

Data Index: 813080 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3025. Min Act: -0.0000

Data Index: 619239 (The Pile)

Max Activating Token Index: 213

Text #14

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1397148 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3058. Min Act: -0.0000

Data Index: 429025 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3101. Min Act: -0.0000

Data Index: 938219 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3489. Min Act: -0.0000

Data Index: 709968 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3048. Min Act: -0.0000

Data Index: 107692 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2891. Min Act: -0.0000

Data Index: 997538 (The Pile)

Max Activating Token Index: 734