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

Dataset: The Pile

Neuron 3834 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.5861. Min Act: -0.0000

Data Index: 750509 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.4079. Min Act: -0.0000

Data Index: 632303 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1609110 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.4036. Min Act: -0.0000

Data Index: 482695 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2876. Min Act: -0.0000

Data Index: 156286 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.4227. Min Act: -0.0000

Data Index: 854559 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1028150 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1467301 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3213. Min Act: -0.0000

Data Index: 921804 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1631232 (The Pile)

Max Activating Token Index: 554

Text #10

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1388375 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.4442. Min Act: -0.0000

Data Index: 447229 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3331. Min Act: -0.0000

Data Index: 54896 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2486. Min Act: -0.0000

Data Index: 389318 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.1747. Min Act: -0.0000

Data Index: 630491 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.1691. Min Act: -0.0000

Data Index: 880790 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.1735. Min Act: -0.0000

Data Index: 463923 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2183. Min Act: -0.0000

Data Index: 959730 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1587330 (The Pile)

Max Activating Token Index: 548

Text #19

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1614139 (The Pile)

Max Activating Token Index: 438