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

Dataset: The Pile

Neuron 3514 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: 0.4001. Min Range: -0.4001

Max Act: 0.4001. Min Act: -0.0000

Data Index: 901186 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3824. Min Act: -0.0000

Data Index: 691550 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1530349 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3462. Min Act: -0.0001

Data Index: 659914 (The Pile)

Max Activating Token Index: 672

Text #4

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3528. Min Act: -0.0000

Data Index: 123614 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1267128 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1544784 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1230864 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3081. Min Act: -0.0000

Data Index: 323315 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1978947 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1143881 (The Pile)

Max Activating Token Index: 386

Text #11

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1426925 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.2906. Min Act: -0.0000

Data Index: 538804 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3080. Min Act: -0.0000

Data Index: 403247 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1686603 (The Pile)

Max Activating Token Index: 558

Text #15

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1966453 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1910767 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3227. Min Act: -0.0000

Data Index: 25012 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3347. Min Act: -0.0000

Data Index: 574912 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1219519 (The Pile)

Max Activating Token Index: 874