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

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

Neuron 5095 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1647. Min Range: -4.1647

Max Act: 4.1647. Min Act: -0.0000

Data Index: 137187 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.6849. Min Act: -0.0000

Data Index: 118699 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.5430. Min Act: -0.0000

Data Index: 1075755 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.3509. Min Act: -0.0000

Data Index: 390807 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.4959. Min Act: -0.0000

Data Index: 986156 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.4098. Min Act: -0.0000

Data Index: 795623 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.3648. Min Act: -0.0000

Data Index: 1017051 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.2031. Min Act: -0.0000

Data Index: 708114 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.3435. Min Act: -0.0000

Data Index: 870443 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.3367. Min Act: -0.0000

Data Index: 838898 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.0303. Min Act: -0.0000

Data Index: 747900 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.3119. Min Act: -0.0000

Data Index: 1330347 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.1405. Min Act: -0.0000

Data Index: 728935 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.1331. Min Act: -0.0000

Data Index: 568529 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 4.1647. Min Range: -4.1647

Max Act: 2.9948. Min Act: -0.0000

Data Index: 815242 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.0887. Min Act: -0.0000

Data Index: 137683 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.2511. Min Act: -0.0000

Data Index: 1304286 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.0980. Min Act: -0.0000

Data Index: 376055 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.2273. Min Act: -0.0000

Data Index: 676961 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 4.1647. Min Range: -4.1647

Max Act: 3.1879. Min Act: -0.0000

Data Index: 395522 (C4 (Web Text))

Max Activating Token Index: 870