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

Dataset: The Pile

Neuron 2224 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5485. Min Range: -7.5485

Max Act: 7.5485. Min Act: -0.0000

Data Index: 167345 (The Pile)

Max Activating Token Index: 885

Text #1

Max Range: 7.5485. Min Range: -7.5485

Max Act: 6.5836. Min Act: -0.0000

Data Index: 128994 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 7.5485. Min Range: -7.5485

Max Act: 5.7764. Min Act: -0.0000

Data Index: 775848 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 7.5485. Min Range: -7.5485

Max Act: 6.0430. Min Act: -0.0000

Data Index: 57971 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 7.5485. Min Range: -7.5485

Max Act: 5.7166. Min Act: -0.0000

Data Index: 909700 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 7.5485. Min Range: -7.5485

Max Act: 5.3193. Min Act: -0.0000

Data Index: 510963 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 7.5485. Min Range: -7.5485

Max Act: 5.1686. Min Act: -0.0000

Data Index: 1621825 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 7.5485. Min Range: -7.5485

Max Act: 5.3055. Min Act: -0.0000

Data Index: 333212 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 7.5485. Min Range: -7.5485

Max Act: 5.0284. Min Act: -0.0000

Data Index: 1527008 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 7.5485. Min Range: -7.5485

Max Act: 5.1689. Min Act: -0.0000

Data Index: 776731 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 7.5485. Min Range: -7.5485

Max Act: 4.8565. Min Act: -0.0000

Data Index: 394883 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 7.5485. Min Range: -7.5485

Max Act: 4.5763. Min Act: -0.0000

Data Index: 546689 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 7.5485. Min Range: -7.5485

Max Act: 4.3101. Min Act: -0.0000

Data Index: 1406041 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 7.5485. Min Range: -7.5485

Max Act: 4.6795. Min Act: -0.0000

Data Index: 151948 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 7.5485. Min Range: -7.5485

Max Act: 3.9440. Min Act: -0.0000

Data Index: 368434 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 7.5485. Min Range: -7.5485

Max Act: 4.0363. Min Act: -0.0000

Data Index: 1372803 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 7.5485. Min Range: -7.5485

Max Act: 4.0863. Min Act: -0.0000

Data Index: 921585 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 7.5485. Min Range: -7.5485

Max Act: 3.8569. Min Act: -0.0000

Data Index: 1775515 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 7.5485. Min Range: -7.5485

Max Act: 3.2749. Min Act: -0.0000

Data Index: 6465 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 7.5485. Min Range: -7.5485

Max Act: 3.6838. Min Act: -0.0000

Data Index: 84529 (The Pile)

Max Activating Token Index: 80