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

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

Neuron 235 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2647. Min Range: -3.2647

Max Act: 3.2289. Min Act: -0.0001

Data Index: 273553 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 3.2647. Min Range: -3.2647

Max Act: 3.2647. Min Act: -0.0000

Data Index: 121530 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 3.2647. Min Range: -3.2647

Max Act: 3.1390. Min Act: -0.0001

Data Index: 1141697 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.8534. Min Act: -0.0000

Data Index: 510030 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.2065. Min Act: -0.0000

Data Index: 1060887 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.6301. Min Act: -0.0001

Data Index: 1230786 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.7822. Min Act: -0.0001

Data Index: 15930 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.5701. Min Act: -0.0001

Data Index: 390260 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.4571. Min Act: -0.0000

Data Index: 73053 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.2327. Min Act: -0.0000

Data Index: 1306035 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.5678. Min Act: -0.0000

Data Index: 60228 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.9981. Min Act: -0.0001

Data Index: 830297 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.1651. Min Act: -0.0001

Data Index: 1122576 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.4864. Min Act: -0.0001

Data Index: 1041386 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.3625. Min Act: -0.0001

Data Index: 367387 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.2168. Min Act: -0.0000

Data Index: 1153051 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.1859. Min Act: -0.0000

Data Index: 386386 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.2990. Min Act: -0.0001

Data Index: 17050 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 3.2647. Min Range: -3.2647

Max Act: 1.9546. Min Act: -0.0001

Data Index: 1175000 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 3.2647. Min Range: -3.2647

Max Act: 2.3821. Min Act: -0.0000

Data Index: 652199 (C4 (Web Text))

Max Activating Token Index: 885