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

Dataset: The Pile

Neuron 1883 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6803. Min Range: -7.6803

Max Act: 7.6803. Min Act: -0.0000

Data Index: 1300817 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 7.6803. Min Range: -7.6803

Max Act: 7.3936. Min Act: -0.0000

Data Index: 864801 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 7.6803. Min Range: -7.6803

Max Act: 7.1030. Min Act: -0.0000

Data Index: 1931687 (The Pile)

Max Activating Token Index: 961

Text #3

Max Range: 7.6803. Min Range: -7.6803

Max Act: 6.3998. Min Act: -0.0000

Data Index: 678950 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 7.6803. Min Range: -7.6803

Max Act: 6.4178. Min Act: -0.0000

Data Index: 1831826 (The Pile)

Max Activating Token Index: 819

Text #5

Max Range: 7.6803. Min Range: -7.6803

Max Act: 6.1899. Min Act: -0.0000

Data Index: 560656 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 7.6803. Min Range: -7.6803

Max Act: 6.4539. Min Act: -0.0000

Data Index: 109962 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.8548. Min Act: -0.0000

Data Index: 85498 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 7.6803. Min Range: -7.6803

Max Act: 6.2578. Min Act: 0.0000

Data Index: 1103080 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.9235. Min Act: -0.0000

Data Index: 469432 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 7.6803. Min Range: -7.6803

Max Act: 6.0599. Min Act: -0.0000

Data Index: 1907155 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.5922. Min Act: -0.0000

Data Index: 1565704 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.5106. Min Act: -0.0000

Data Index: 1327139 (The Pile)

Max Activating Token Index: 620

Text #13

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.5268. Min Act: -0.0000

Data Index: 1273880 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.4630. Min Act: -0.0000

Data Index: 628104 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.4130. Min Act: -0.0000

Data Index: 1246394 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.5175. Min Act: -0.0000

Data Index: 1578486 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.3024. Min Act: -0.0000

Data Index: 746783 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.1076. Min Act: -0.0000

Data Index: 1403435 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 7.6803. Min Range: -7.6803

Max Act: 5.4421. Min Act: -0.0000

Data Index: 925621 (The Pile)

Max Activating Token Index: 457