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

Dataset: The Pile

Neuron 3673 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.7897. Min Act: -0.0000

Data Index: 46563 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1956223 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.7228. Min Act: -0.0000

Data Index: 931052 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.7116. Min Act: -0.0000

Data Index: 713518 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6881. Min Act: -0.0000

Data Index: 321681 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1191349 (The Pile)

Max Activating Token Index: 775

Text #6

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1380841 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6933. Min Act: -0.0000

Data Index: 373269 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1370265 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6568. Min Act: -0.0000

Data Index: 921216 (The Pile)

Max Activating Token Index: 358

Text #10

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6783. Min Act: -0.0000

Data Index: 207350 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1099969 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6399. Min Act: -0.0000

Data Index: 494280 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6829. Min Act: -0.0000

Data Index: 946530 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1672869 (The Pile)

Max Activating Token Index: 855

Text #15

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6583. Min Act: -0.0000

Data Index: 321424 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1001111 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5932. Min Act: -0.0000

Data Index: 541497 (The Pile)

Max Activating Token Index: 943

Text #18

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6916. Min Act: -0.0000

Data Index: 783810 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6702. Min Act: -0.0000

Data Index: 290830 (The Pile)

Max Activating Token Index: 77