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

Dataset: The Pile

Neuron 3937 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: 0.7825. Min Range: -0.7825

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1212020 (The Pile)

Max Activating Token Index: 179

Text #1

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6900. Min Act: -0.0000

Data Index: 437264 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1242357 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7518. Min Act: -0.0000

Data Index: 194235 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7825. Min Act: -0.0000

Data Index: 141517 (The Pile)

Max Activating Token Index: 379

Text #5

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7534. Min Act: -0.0000

Data Index: 364380 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6799. Min Act: -0.0000

Data Index: 72177 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.5541. Min Act: -0.0000

Data Index: 480072 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1240347 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1903900 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1110988 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6006. Min Act: -0.0000

Data Index: 257718 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.5160. Min Act: -0.0000

Data Index: 228580 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1407491 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.4877. Min Act: -0.0000

Data Index: 950601 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1408717 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.4689. Min Act: -0.0000

Data Index: 512340 (The Pile)

Max Activating Token Index: 303

Text #17

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1488798 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.4284. Min Act: -0.0000

Data Index: 865450 (The Pile)

Max Activating Token Index: 749

Text #19

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1359058 (The Pile)

Max Activating Token Index: 745