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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3291 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.6956. Min Act: -0.0000

Data Index: 439713 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.4659. Min Act: -0.0000

Data Index: 318379 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.4987. Min Act: -0.0000

Data Index: 629073 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.2709. Min Act: -0.0000

Data Index: 266222 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1170823 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.3026. Min Act: -0.0000

Data Index: 433533 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.3007. Min Act: -0.0000

Data Index: 697528 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.3899. Min Act: -0.0000

Data Index: 531725 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.2221. Min Act: -0.0000

Data Index: 675077 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 2.6956. Min Range: -2.6956

Max Act: 1.8922. Min Act: -0.0000

Data Index: 959557 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.2193. Min Act: -0.0000

Data Index: 570045 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 2.6956. Min Range: -2.6956

Max Act: 1.9409. Min Act: -0.0000

Data Index: 433696 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.1918. Min Act: -0.0000

Data Index: 524864 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.0515. Min Act: -0.0000

Data Index: 382663 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.0598. Min Act: -0.0000

Data Index: 1225780 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.1469. Min Act: -0.0000

Data Index: 1061824 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.1130. Min Act: -0.0000

Data Index: 1080773 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.1802. Min Act: -0.0000

Data Index: 1011548 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 2.6956. Min Range: -2.6956

Max Act: 2.1623. Min Act: -0.0000

Data Index: 640263 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 2.6956. Min Range: -2.6956

Max Act: 1.9350. Min Act: -0.0000

Data Index: 583116 (C4 (Web Text))

Max Activating Token Index: 936