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

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

Neuron 870 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: 0.3841. Min Range: -0.3841

Max Act: 0.3841. Min Act: -0.0000

Data Index: 130792 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1237621 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1231572 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2218. Min Act: -0.0000

Data Index: 129159 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1334511 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1218511 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1734. Min Act: -0.0000

Data Index: 798951 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2215. Min Act: -0.0000

Data Index: 801169 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2143. Min Act: -0.0000

Data Index: 746222 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1952. Min Act: -0.0000

Data Index: 166374 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1817. Min Act: -0.0001

Data Index: 1072059 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1883. Min Act: -0.0000

Data Index: 420928 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1047031 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1860. Min Act: -0.0000

Data Index: 806186 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1917. Min Act: -0.0000

Data Index: 65206 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2118. Min Act: -0.0000

Data Index: 898443 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1241396 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1235421 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1717. Min Act: -0.0000

Data Index: 681059 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1198465 (C4 (Web Text))

Max Activating Token Index: 112