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

Dataset: The Pile

Neuron 5040 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1355748 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2456. Min Act: -0.0000

Data Index: 138445 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2869. Min Act: -0.0000

Data Index: 873399 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1559209 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2661. Min Act: -0.0000

Data Index: 734210 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2497. Min Act: -0.0001

Data Index: 747945 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2656. Min Act: -0.0000

Data Index: 93379 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2517. Min Act: -0.0000

Data Index: 401546 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2512. Min Act: -0.0001

Data Index: 1602407 (The Pile)

Max Activating Token Index: 474

Text #9

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1556030 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2283. Min Act: -0.0001

Data Index: 249904 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1934648 (The Pile)

Max Activating Token Index: 467

Text #12

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2325. Min Act: -0.0000

Data Index: 162306 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1490140 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1296670 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1136482 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2153. Min Act: -0.0000

Data Index: 837568 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1959919 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1112872 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2222. Min Act: -0.0001

Data Index: 425498 (The Pile)

Max Activating Token Index: 609