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

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

Neuron 5234 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.2505. Min Act: -0.0002

Data Index: 65321 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.1578. Min Act: -0.0002

Data Index: 1079428 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.1364. Min Act: -0.0002

Data Index: 426499 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0859. Min Act: -0.0002

Data Index: 643912 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0564. Min Act: -0.0002

Data Index: 534602 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0442. Min Act: -0.0002

Data Index: 1336835 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0448. Min Act: -0.0002

Data Index: 134939 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0307. Min Act: -0.0002

Data Index: 24031 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0281. Min Act: -0.0002

Data Index: 925877 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0139. Min Act: -0.0002

Data Index: 552518 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0134. Min Act: -0.0002

Data Index: 809002 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9884. Min Act: -0.0002

Data Index: 575486 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0169. Min Act: -0.0002

Data Index: 1213521 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9624. Min Act: -0.0002

Data Index: 409427 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9636. Min Act: -0.0002

Data Index: 1057233 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9935. Min Act: -0.0002

Data Index: 1229427 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9812. Min Act: -0.0002

Data Index: 1178984 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0019. Min Act: -0.0002

Data Index: 1301550 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9882. Min Act: -0.0002

Data Index: 1158180 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9748. Min Act: -0.0002

Data Index: 1004768 (C4 (Web Text))

Max Activating Token Index: 417