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

Dataset: The Pile

Neuron 422 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: 0.3192. Min Range: -0.3192

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1744075 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1125909 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1508690 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1674876 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2530. Min Act: -0.0000

Data Index: 693296 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2625. Min Act: -0.0000

Data Index: 744067 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1482059 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1500231 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1916933 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2585. Min Act: -0.0000

Data Index: 663056 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2583. Min Act: -0.0000

Data Index: 541751 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2658. Min Act: -0.0000

Data Index: 602404 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2386. Min Act: -0.0000

Data Index: 946514 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2609. Min Act: -0.0000

Data Index: 916899 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1854979 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2356. Min Act: -0.0000

Data Index: 753702 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2402. Min Act: -0.0000

Data Index: 621256 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2386. Min Act: -0.0000

Data Index: 167007 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1256914 (The Pile)

Max Activating Token Index: 255

Text #19

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2289. Min Act: -0.0000

Data Index: 675216 (The Pile)

Max Activating Token Index: 167