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

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

Neuron 3844 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.9305. Min Act: -0.0001

Data Index: 99436 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1167261 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7815. Min Act: -0.0001

Data Index: 962588 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8317. Min Act: -0.0001

Data Index: 58442 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8627. Min Act: -0.0001

Data Index: 1045887 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.9952. Min Act: -0.0001

Data Index: 416027 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8622. Min Act: -0.0001

Data Index: 1226917 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7372. Min Act: -0.0001

Data Index: 245764 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8329. Min Act: -0.0001

Data Index: 718529 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7573. Min Act: -0.0001

Data Index: 237596 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8904. Min Act: -0.0001

Data Index: 918073 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8139. Min Act: -0.0001

Data Index: 1326523 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7677. Min Act: -0.0001

Data Index: 989399 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8514. Min Act: -0.0001

Data Index: 216192 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7718. Min Act: -0.0001

Data Index: 1208716 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7481. Min Act: -0.0001

Data Index: 120992 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8283. Min Act: -0.0001

Data Index: 1297466 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7917. Min Act: -0.0001

Data Index: 923545 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7371. Min Act: -0.0001

Data Index: 1237872 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7591. Min Act: -0.0001

Data Index: 709839 (C4 (Web Text))

Max Activating Token Index: 933