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

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

Neuron 3332 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: 5.9297. Min Range: -5.9297

Max Act: 5.9297. Min Act: -0.0000

Data Index: 1356479 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 5.9297. Min Range: -5.9297

Max Act: 3.6901. Min Act: -0.0000

Data Index: 223990 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 5.9297. Min Range: -5.9297

Max Act: 3.8254. Min Act: -0.0000

Data Index: 15085 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 5.9297. Min Range: -5.9297

Max Act: 3.7927. Min Act: -0.0000

Data Index: 498537 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 5.9297. Min Range: -5.9297

Max Act: 3.2861. Min Act: -0.0000

Data Index: 318749 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 5.9297. Min Range: -5.9297

Max Act: 3.4007. Min Act: -0.0000

Data Index: 962488 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 5.9297. Min Range: -5.9297

Max Act: 3.3545. Min Act: -0.0000

Data Index: 675794 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 5.9297. Min Range: -5.9297

Max Act: 3.0578. Min Act: -0.0000

Data Index: 247383 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 5.9297. Min Range: -5.9297

Max Act: 3.1893. Min Act: -0.0000

Data Index: 872654 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.8605. Min Act: -0.0000

Data Index: 1029124 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.9844. Min Act: -0.0000

Data Index: 1258981 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 5.9297. Min Range: -5.9297

Max Act: 3.0823. Min Act: -0.0000

Data Index: 583881 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.9941. Min Act: -0.0000

Data Index: 75272 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.9844. Min Act: -0.0000

Data Index: 120012 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.8518. Min Act: -0.0000

Data Index: 615076 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.6421. Min Act: -0.0000

Data Index: 1101584 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.7622. Min Act: -0.0000

Data Index: 1174028 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.9846. Min Act: -0.0000

Data Index: 171125 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.8498. Min Act: -0.0000

Data Index: 759999 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 5.9297. Min Range: -5.9297

Max Act: 2.6694. Min Act: -0.0000

Data Index: 882142 (C4 (Web Text))

Max Activating Token Index: 385