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

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

Neuron 2553 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.7034. Min Act: -0.0001

Data Index: 1000699 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.6942. Min Act: -0.0001

Data Index: 123023 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.4614. Min Act: -0.0001

Data Index: 540674 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.6793. Min Act: -0.0001

Data Index: 746298 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.4885. Min Act: -0.0001

Data Index: 1268524 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.5852. Min Act: -0.0001

Data Index: 940281 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.4959. Min Act: -0.0001

Data Index: 281565 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.5832. Min Act: -0.0001

Data Index: 503306 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.3713. Min Act: -0.0001

Data Index: 1100958 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.4425. Min Act: -0.0001

Data Index: 456447 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.4823. Min Act: -0.0001

Data Index: 1106664 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.3851. Min Act: -0.0001

Data Index: 1053793 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.3730. Min Act: -0.0001

Data Index: 917065 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.4427. Min Act: -0.0001

Data Index: 630940 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.3417. Min Act: -0.0001

Data Index: 686728 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.3034. Min Act: -0.0001

Data Index: 697616 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.3048. Min Act: -0.0001

Data Index: 812290 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.3514. Min Act: -0.0001

Data Index: 625214 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.3639. Min Act: -0.0001

Data Index: 334980 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.7034. Min Range: -1.7034

Max Act: 1.4323. Min Act: -0.0001

Data Index: 1359439 (C4 (Web Text))

Max Activating Token Index: 646