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

Dataset: The Pile

Neuron 3480 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: 5.3708. Min Range: -5.3708

Max Act: 5.3708. Min Act: -0.0000

Data Index: 1204539 (The Pile)

Max Activating Token Index: 488

Text #1

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.9328. Min Act: -0.0000

Data Index: 1376444 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.8462. Min Act: -0.0000

Data Index: 1261187 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 5.3708. Min Range: -5.3708

Max Act: 5.0420. Min Act: -0.0000

Data Index: 976014 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.7814. Min Act: -0.0000

Data Index: 169166 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.5356. Min Act: -0.0000

Data Index: 92520 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.6850. Min Act: -0.0000

Data Index: 1277818 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.5564. Min Act: -0.0000

Data Index: 1497135 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.4139. Min Act: -0.0000

Data Index: 1165245 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.3673. Min Act: -0.0000

Data Index: 255271 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.5383. Min Act: -0.0000

Data Index: 876573 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.3362. Min Act: -0.0000

Data Index: 1904883 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.4919. Min Act: -0.0000

Data Index: 295073 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.4661. Min Act: -0.0000

Data Index: 569822 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.3472. Min Act: -0.0000

Data Index: 716207 (The Pile)

Max Activating Token Index: 692

Text #15

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.3461. Min Act: -0.0000

Data Index: 279547 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.6423. Min Act: -0.0000

Data Index: 1379069 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.2981. Min Act: -0.0000

Data Index: 442538 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.4706. Min Act: -0.0000

Data Index: 1832208 (The Pile)

Max Activating Token Index: 263

Text #19

Max Range: 5.3708. Min Range: -5.3708

Max Act: 4.2814. Min Act: -0.0000

Data Index: 506601 (The Pile)

Max Activating Token Index: 349