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

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

Neuron 1075 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: 1.3859. Min Range: -1.3859

Max Act: 1.3859. Min Act: -0.0001

Data Index: 802741 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.2772. Min Act: -0.0001

Data Index: 242636 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.2715. Min Act: -0.0001

Data Index: 745548 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.2603. Min Act: -0.0001

Data Index: 38416 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.1388. Min Act: -0.0001

Data Index: 661985 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.2604. Min Act: -0.0001

Data Index: 430067 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.9489. Min Act: -0.0001

Data Index: 3253 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.1029. Min Act: -0.0001

Data Index: 567462 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.1802. Min Act: -0.0001

Data Index: 343178 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.1280. Min Act: -0.0001

Data Index: 301589 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0364. Min Act: -0.0001

Data Index: 1194696 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0747. Min Act: -0.0001

Data Index: 123120 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.9968. Min Act: -0.0001

Data Index: 532057 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0072. Min Act: -0.0001

Data Index: 669584 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.1522. Min Act: -0.0001

Data Index: 1016279 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.1815. Min Act: -0.0001

Data Index: 375854 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0482. Min Act: -0.0001

Data Index: 52207 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0788. Min Act: -0.0001

Data Index: 1307469 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.1123. Min Act: -0.0001

Data Index: 242806 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0963. Min Act: -0.0001

Data Index: 1245736 (C4 (Web Text))

Max Activating Token Index: 963