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

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

Neuron 2443 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: 5.2386. Min Range: -5.2386

Max Act: 5.2386. Min Act: -0.0001

Data Index: 466277 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 5.2386. Min Range: -5.2386

Max Act: 4.1351. Min Act: -0.0001

Data Index: 286092 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 5.2386. Min Range: -5.2386

Max Act: 3.4537. Min Act: -0.0001

Data Index: 915928 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 5.2386. Min Range: -5.2386

Max Act: 3.4494. Min Act: -0.0001

Data Index: 1122608 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 5.2386. Min Range: -5.2386

Max Act: 3.1733. Min Act: -0.0001

Data Index: 1137058 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.7988. Min Act: -0.0001

Data Index: 257028 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.6460. Min Act: -0.0001

Data Index: 1181472 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.7799. Min Act: -0.0001

Data Index: 760574 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.5703. Min Act: -0.0001

Data Index: 104501 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.8084. Min Act: -0.0001

Data Index: 903491 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.4995. Min Act: -0.0001

Data Index: 776133 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.5929. Min Act: -0.0001

Data Index: 622885 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.5798. Min Act: -0.0001

Data Index: 492231 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.6659. Min Act: -0.0001

Data Index: 90595 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.4045. Min Act: -0.0001

Data Index: 201836 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.4080. Min Act: -0.0001

Data Index: 731374 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.4746. Min Act: -0.0001

Data Index: 277616 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.3535. Min Act: -0.0001

Data Index: 607623 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.3994. Min Act: -0.0001

Data Index: 345350 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 5.2386. Min Range: -5.2386

Max Act: 2.2809. Min Act: -0.0001

Data Index: 1202055 (C4 (Web Text))

Max Activating Token Index: 559