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

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

Neuron 4207 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.7223. Min Act: -0.0000

Data Index: 593178 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.7142. Min Act: -0.0000

Data Index: 157199 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.6948. Min Act: -0.0000

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.7942. Min Act: -0.0000

Data Index: 1200088 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.7029. Min Act: -0.0000

Data Index: 1076585 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1262880 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.7857. Min Act: -0.0000

Data Index: 1043691 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.6113. Min Act: -0.0000

Data Index: 1271521 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.8365. Min Act: -0.0000

Data Index: 585616 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.5582. Min Act: -0.0000

Data Index: 396252 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.5739. Min Act: -0.0000

Data Index: 202886 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.5605. Min Act: -0.0000

Data Index: 727060 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.4737. Min Act: -0.0000

Data Index: 218766 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1219619 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.6181. Min Act: -0.0000

Data Index: 371548 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.5217. Min Act: -0.0000

Data Index: 379366 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.6105. Min Act: -0.0000

Data Index: 407825 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.5796. Min Act: -0.0000

Data Index: 869055 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1183352 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.8365. Min Range: -1.8365

Max Act: 1.4619. Min Act: -0.0000

Data Index: 59111 (C4 (Web Text))

Max Activating Token Index: 585