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

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

Neuron 1653 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.2722. Min Act: -0.0000

Data Index: 258749 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.0457. Min Act: -0.0000

Data Index: 555 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.9082. Min Act: -0.0000

Data Index: 943908 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1318076 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.7839. Min Act: -0.0000

Data Index: 12509 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.7580. Min Act: -0.0000

Data Index: 450701 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.8109. Min Act: -0.0000

Data Index: 619620 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1217345 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.7020. Min Act: -0.0000

Data Index: 408150 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.7393. Min Act: -0.0000

Data Index: 519141 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1290212 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1179399 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.6737. Min Act: -0.0000

Data Index: 112710 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1358755 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1321099 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.6900. Min Act: -0.0000

Data Index: 624126 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.7144. Min Act: -0.0000

Data Index: 660635 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.6429. Min Act: -0.0000

Data Index: 638923 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.6163. Min Act: -0.0000

Data Index: 27090 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.6263. Min Act: -0.0000

Data Index: 49672 (C4 (Web Text))

Max Activating Token Index: 925