Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2332 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 7.7663. Min Range: -7.7663

Max Act: 7.4337. Min Act: -0.0000

Data Index: 1715824 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 7.7663. Min Range: -7.7663

Max Act: 7.7663. Min Act: -0.0000

Data Index: 642083 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 7.7663. Min Range: -7.7663

Max Act: 7.1854. Min Act: -0.0000

Data Index: 1237975 (The Pile)

Max Activating Token Index: 447

Text #3

Max Range: 7.7663. Min Range: -7.7663

Max Act: 7.1244. Min Act: -0.0000

Data Index: 1272175 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.6933. Min Act: -0.0000

Data Index: 386992 (The Pile)

Max Activating Token Index: 713

Text #5

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.8869. Min Act: -0.0000

Data Index: 1752491 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.2919. Min Act: -0.0000

Data Index: 411900 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.6763. Min Act: -0.0000

Data Index: 1230255 (The Pile)

Max Activating Token Index: 623

Text #8

Max Range: 7.7663. Min Range: -7.7663

Max Act: 5.8998. Min Act: -0.0000

Data Index: 880992 (The Pile)

Max Activating Token Index: 365

Text #9

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.3876. Min Act: -0.0000

Data Index: 387694 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.1447. Min Act: -0.0000

Data Index: 1811646 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 7.7663. Min Range: -7.7663

Max Act: 5.7592. Min Act: -0.0000

Data Index: 313911 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.1443. Min Act: -0.0000

Data Index: 1826573 (The Pile)

Max Activating Token Index: 749

Text #13

Max Range: 7.7663. Min Range: -7.7663

Max Act: 5.6313. Min Act: -0.0000

Data Index: 1379850 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.1001. Min Act: -0.0001

Data Index: 1298642 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.1830. Min Act: -0.0000

Data Index: 924188 (The Pile)

Max Activating Token Index: 792

Text #16

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.5118. Min Act: -0.0000

Data Index: 610381 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 7.7663. Min Range: -7.7663

Max Act: 5.9938. Min Act: -0.0000

Data Index: 1897281 (The Pile)

Max Activating Token Index: 563

Text #18

Max Range: 7.7663. Min Range: -7.7663

Max Act: 6.1438. Min Act: -0.0000

Data Index: 197186 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 7.7663. Min Range: -7.7663

Max Act: 5.7495. Min Act: -0.0000

Data Index: 143250 (The Pile)

Max Activating Token Index: 443