Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2069 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4950. Min Act: -0.0000

Data Index: 910323 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1765087 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3197. Min Act: -0.0000

Data Index: 498054 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3097. Min Act: 0.0000

Data Index: 1835186 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1032449 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3144. Min Act: -0.0000

Data Index: 356771 (The Pile)

Max Activating Token Index: 487

Text #6

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2697. Min Act: -0.0000

Data Index: 908758 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2624. Min Act: -0.0000

Data Index: 290336 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1875253 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2486. Min Act: -0.0000

Data Index: 340065 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2891. Min Act: -0.0000

Data Index: 982167 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2596. Min Act: -0.0000

Data Index: 265434 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1225813 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2435. Min Act: -0.0000

Data Index: 890797 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2424. Min Act: -0.0000

Data Index: 14050 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1556677 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1181377 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1198061 (The Pile)

Max Activating Token Index: 611

Text #18

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2415. Min Act: -0.0000

Data Index: 24170 (The Pile)

Max Activating Token Index: 77

Text #19

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1199096 (The Pile)

Max Activating Token Index: 851