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

Dataset: The Pile

Neuron 3580 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6920. Min Act: -0.0000

Data Index: 1439259 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.3267. Min Act: -0.0000

Data Index: 445169 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.0850. Min Act: -0.0000

Data Index: 411389 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.9090. Min Act: -0.0000

Data Index: 924764 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.9858. Min Act: -0.0000

Data Index: 123281 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.8552. Min Act: -0.0000

Data Index: 555954 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.9993. Min Act: -0.0000

Data Index: 1635303 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.7115. Min Act: -0.0000

Data Index: 954732 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.7649. Min Act: -0.0000

Data Index: 819393 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.8821. Min Act: -0.0000

Data Index: 659152 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.7491. Min Act: -0.0000

Data Index: 1339707 (The Pile)

Max Activating Token Index: 425

Text #11

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.8516. Min Act: -0.0000

Data Index: 1349853 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.8392. Min Act: -0.0000

Data Index: 1110311 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.1074. Min Act: -0.0000

Data Index: 460442 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.8348. Min Act: -0.0000

Data Index: 925758 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.6379. Min Act: -0.0000

Data Index: 1699615 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.6521. Min Act: -0.0000

Data Index: 1272907 (The Pile)

Max Activating Token Index: 653

Text #17

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.9144. Min Act: -0.0000

Data Index: 412152 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.8914. Min Act: -0.0000

Data Index: 1787710 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 3.6920. Min Range: -3.6920

Max Act: 2.5191. Min Act: -0.0000

Data Index: 1956160 (The Pile)

Max Activating Token Index: 676