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

Dataset: The Pile

Neuron 4511 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: 3.8434. Min Range: -3.8434

Max Act: 3.8434. Min Act: -0.0000

Data Index: 1111171 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.4284. Min Act: -0.0000

Data Index: 1124112 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.4407. Min Act: -0.0000

Data Index: 1616714 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.2621. Min Act: -0.0000

Data Index: 965851 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.4533. Min Act: -0.0000

Data Index: 1150502 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.0667. Min Act: -0.0000

Data Index: 1280557 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.1418. Min Act: -0.0000

Data Index: 427349 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.7597. Min Act: -0.0000

Data Index: 232290 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.7442. Min Act: -0.0000

Data Index: 1969569 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.2772. Min Act: -0.0000

Data Index: 364862 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.8051. Min Act: -0.0000

Data Index: 1848853 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.6470. Min Act: -0.0000

Data Index: 1440337 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.6390. Min Act: -0.0000

Data Index: 1215061 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.6264. Min Act: -0.0000

Data Index: 347309 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.7409. Min Act: -0.0000

Data Index: 983838 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.3492. Min Act: -0.0000

Data Index: 683937 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.5923. Min Act: -0.0000

Data Index: 214125 (The Pile)

Max Activating Token Index: 71

Text #17

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.5775. Min Act: -0.0000

Data Index: 51995 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.2315. Min Act: -0.0000

Data Index: 1708202 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 3.8434. Min Range: -3.8434

Max Act: 2.5561. Min Act: -0.0000

Data Index: 1096468 (The Pile)

Max Activating Token Index: 360