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

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

Neuron 138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1306. Min Act: -0.0000

Data Index: 379538 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1348. Min Act: -0.0000

Data Index: 359430 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1058668 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1135. Min Act: -0.0000

Data Index: 28 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1106. Min Act: -0.0000

Data Index: 418376 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0988. Min Act: -0.0000

Data Index: 368077 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0990. Min Act: -0.0000

Data Index: 26651 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1026. Min Act: -0.0000

Data Index: 638664 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1032. Min Act: -0.0000

Data Index: 801040 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1002. Min Act: -0.0000

Data Index: 2634 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0999. Min Act: -0.0000

Data Index: 510041 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0884. Min Act: -0.0000

Data Index: 20938 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1177697 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1175913 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1135363 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0797. Min Act: -0.0000

Data Index: 184396 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0866. Min Act: -0.0000

Data Index: 211011 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1051513 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1240234 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0828. Min Act: -0.0000

Data Index: 330350 (C4 (Web Text))

Max Activating Token Index: 119