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

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

Neuron 5 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1796. Min Range: -3.1796

Max Act: 3.1796. Min Act: -0.0000

Data Index: 1205162 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.8656. Min Act: -0.0000

Data Index: 1270139 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.8934. Min Act: -0.0000

Data Index: 38452 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.6349. Min Act: -0.0000

Data Index: 506495 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.7161. Min Act: -0.0000

Data Index: 289846 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.5778. Min Act: -0.0000

Data Index: 603602 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.7009. Min Act: -0.0000

Data Index: 496743 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.6825. Min Act: -0.0000

Data Index: 762182 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.4181. Min Act: -0.0000

Data Index: 120625 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.7984. Min Act: -0.0000

Data Index: 869866 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.6674. Min Act: -0.0000

Data Index: 176268 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.6521. Min Act: -0.0000

Data Index: 917976 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.5096. Min Act: -0.0000

Data Index: 1122999 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.6163. Min Act: -0.0000

Data Index: 94232 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.6056. Min Act: -0.0000

Data Index: 1330726 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.5591. Min Act: -0.0000

Data Index: 34088 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.5627. Min Act: -0.0000

Data Index: 43817 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.4923. Min Act: -0.0000

Data Index: 1217204 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.5231. Min Act: -0.0000

Data Index: 586928 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 3.1796. Min Range: -3.1796

Max Act: 2.6468. Min Act: -0.0000

Data Index: 1177828 (C4 (Web Text))

Max Activating Token Index: 977