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

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

Neuron 3660 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: 1.3489. Min Range: -1.3489

Max Act: 1.3482. Min Act: -0.0002

Data Index: 45803 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.3489. Min Act: -0.0002

Data Index: 213736 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2597. Min Act: -0.0002

Data Index: 452675 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2639. Min Act: -0.0002

Data Index: 543761 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2393. Min Act: -0.0002

Data Index: 921944 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1786. Min Act: -0.0002

Data Index: 1362434 (Python Code)

Max Activating Token Index: 410

Text #6

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1240. Min Act: -0.0002

Data Index: 1244147 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1186. Min Act: -0.0002

Data Index: 10435 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1206. Min Act: -0.0002

Data Index: 225567 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1167. Min Act: -0.0002

Data Index: 898169 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1218. Min Act: -0.0002

Data Index: 642406 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1048. Min Act: -0.0002

Data Index: 735029 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0841. Min Act: -0.0002

Data Index: 610896 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0632. Min Act: -0.0002

Data Index: 1129878 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0761. Min Act: -0.0002

Data Index: 1172429 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1120. Min Act: -0.0002

Data Index: 409817 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0667. Min Act: -0.0002

Data Index: 304542 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0774. Min Act: -0.0002

Data Index: 239256 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0668. Min Act: -0.0002

Data Index: 1260994 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0619. Min Act: -0.0002

Data Index: 873801 (C4 (Web Text))

Max Activating Token Index: 318