Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 913 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.4345. Min Act: -0.0000

Data Index: 621820 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.4081. Min Act: -0.0000

Data Index: 955075 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1517397 (The Pile)

Max Activating Token Index: 106

Text #3

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1952033 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1651380 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3796. Min Act: 0.0000

Data Index: 1757295 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1127185 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1965136 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3572. Min Act: -0.0001

Data Index: 359373 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3557. Min Act: 0.0000

Data Index: 335056 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1086315 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3538. Min Act: -0.0000

Data Index: 387959 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1697173 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3401. Min Act: -0.0000

Data Index: 177952 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1509251 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3384. Min Act: 0.0000

Data Index: 1142355 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3264. Min Act: -0.0000

Data Index: 435329 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3251. Min Act: -0.0000

Data Index: 994722 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3514. Min Act: 0.0001

Data Index: 583905 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1777630 (The Pile)

Max Activating Token Index: 294