Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2481 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1443. Min Range: -1.1443

Max Act: 1.1443. Min Act: -0.0001

Data Index: 412680 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.1443. Min Range: -1.1443

Max Act: 1.0194. Min Act: -0.0001

Data Index: 374637 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.1443. Min Range: -1.1443

Max Act: 1.0198. Min Act: -0.0001

Data Index: 875769 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9711. Min Act: -0.0001

Data Index: 1115155 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9626. Min Act: -0.0001

Data Index: 630685 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8647. Min Act: -0.0001

Data Index: 1067194 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9134. Min Act: -0.0001

Data Index: 753817 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8432. Min Act: -0.0001

Data Index: 12197 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 1.1443. Min Range: -1.1443

Max Act: 1.0840. Min Act: -0.0001

Data Index: 1000816 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8720. Min Act: -0.0001

Data Index: 424329 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9260. Min Act: -0.0001

Data Index: 1035971 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8877. Min Act: -0.0001

Data Index: 158584 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8616. Min Act: -0.0001

Data Index: 1176824 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8662. Min Act: -0.0001

Data Index: 884897 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8370. Min Act: -0.0001

Data Index: 1095237 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8509. Min Act: -0.0001

Data Index: 503595 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8519. Min Act: -0.0001

Data Index: 936237 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8767. Min Act: -0.0001

Data Index: 1297833 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8225. Min Act: -0.0001

Data Index: 1341865 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8937. Min Act: -0.0001

Data Index: 938308 (C4 (Web Text))

Max Activating Token Index: 892