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

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

Neuron 3141 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1380565 (Python Code)

Max Activating Token Index: 943

Text #1

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1160. Min Act: -0.0001

Data Index: 192143 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1288113 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0942. Min Act: -0.0001

Data Index: 636060 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0983. Min Act: -0.0001

Data Index: 620085 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1570962 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1587952 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0741. Min Act: -0.0001

Data Index: 623371 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0820. Min Act: -0.0001

Data Index: 981870 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1219455 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0910. Min Act: -0.0001

Data Index: 655187 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0800. Min Act: -0.0001

Data Index: 905201 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0864. Min Act: -0.0001

Data Index: 798870 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0783. Min Act: -0.0001

Data Index: 180972 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0881. Min Act: -0.0001

Data Index: 338960 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0783. Min Act: -0.0001

Data Index: 372911 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1523256 (Python Code)

Max Activating Token Index: 279

Text #17

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1186080 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0780. Min Act: -0.0001

Data Index: 994750 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1155013 (C4 (Web Text))

Max Activating Token Index: 954