Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 89 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2759. Min Act: -0.0000

Data Index: 383241 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2573. Min Act: -0.0001

Data Index: 836538 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2122. Min Act: -0.0001

Data Index: 198407 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2214. Min Act: -0.0001

Data Index: 825364 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2352. Min Act: -0.0000

Data Index: 856421 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2152. Min Act: -0.0001

Data Index: 572518 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1054877 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2132. Min Act: -0.0000

Data Index: 814153 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1199609 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2065. Min Act: -0.0000

Data Index: 82608 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2225. Min Act: -0.0000

Data Index: 480518 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1326624 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1915. Min Act: -0.0000

Data Index: 228235 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2032. Min Act: -0.0000

Data Index: 812673 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2106. Min Act: -0.0001

Data Index: 679742 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1934. Min Act: -0.0000

Data Index: 737071 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1986. Min Act: -0.0000

Data Index: 259150 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1941. Min Act: -0.0000

Data Index: 307521 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1242073 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1623. Min Act: -0.0001

Data Index: 667171 (C4 (Web Text))

Max Activating Token Index: 702