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

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

Neuron 48 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.4065. Min Act: -0.0001

Data Index: 1021100 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.4334. Min Act: -0.0001

Data Index: 657345 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.4411. Min Act: -0.0001

Data Index: 681140 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2302. Min Act: -0.0001

Data Index: 427945 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.4368. Min Act: -0.0001

Data Index: 800511 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1926. Min Act: -0.0002

Data Index: 986411 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2989. Min Act: -0.0001

Data Index: 779573 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2968. Min Act: -0.0001

Data Index: 598170 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.3587. Min Act: -0.0001

Data Index: 1214698 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.3509. Min Act: -0.0001

Data Index: 833416 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2884. Min Act: -0.0001

Data Index: 929733 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 1.4411. Min Range: -1.4411

Max Act: 0.9945. Min Act: -0.0001

Data Index: 817393 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.3826. Min Act: -0.0001

Data Index: 140027 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1306. Min Act: -0.0001

Data Index: 642710 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2430. Min Act: -0.0001

Data Index: 91297 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0601. Min Act: -0.0001

Data Index: 276471 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1560. Min Act: -0.0001

Data Index: 896021 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.3142. Min Act: -0.0001

Data Index: 542813 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2658. Min Act: -0.0001

Data Index: 106777 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 1.4411. Min Range: -1.4411

Max Act: 0.8170. Min Act: -0.0001

Data Index: 295577 (C4 (Web Text))

Max Activating Token Index: 317