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

Dataset: The Pile

Neuron 3601 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.6915. Min Act: -0.0000

Data Index: 1878053 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.5888. Min Act: -0.0000

Data Index: 307514 (The Pile)

Max Activating Token Index: 250

Text #2

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.6309. Min Act: -0.0000

Data Index: 1868889 (The Pile)

Max Activating Token Index: 950

Text #3

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.5343. Min Act: -0.0000

Data Index: 346385 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.5803. Min Act: -0.0000

Data Index: 393119 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.5445. Min Act: -0.0000

Data Index: 793843 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1711095 (The Pile)

Max Activating Token Index: 140

Text #7

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.4645. Min Act: -0.0000

Data Index: 1420156 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.4489. Min Act: -0.0000

Data Index: 272109 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3618. Min Act: -0.0000

Data Index: 871992 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3461. Min Act: -0.0000

Data Index: 106863 (The Pile)

Max Activating Token Index: 533

Text #11

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3440. Min Act: -0.0000

Data Index: 538407 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1474851 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3282. Min Act: -0.0000

Data Index: 1478203 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.2458. Min Act: -0.0000

Data Index: 149774 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3763. Min Act: -0.0000

Data Index: 727206 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.2755. Min Act: -0.0000

Data Index: 650678 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.2719. Min Act: -0.0000

Data Index: 558621 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.1968. Min Act: -0.0000

Data Index: 319329 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.2529. Min Act: -0.0000

Data Index: 699280 (The Pile)

Max Activating Token Index: 403