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

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

Neuron 5592 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: 0.3221. Min Range: -0.3221

Max Act: 0.3221. Min Act: -0.0001

Data Index: 1512300 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1656329 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2785. Min Act: -0.0001

Data Index: 1399821 (Python Code)

Max Activating Token Index: 741

Text #3

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2854. Min Act: -0.0001

Data Index: 1472105 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2549. Min Act: -0.0001

Data Index: 1551865 (Python Code)

Max Activating Token Index: 872

Text #5

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1627586 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1481582 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2499. Min Act: -0.0001

Data Index: 1537583 (Python Code)

Max Activating Token Index: 654

Text #8

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2576. Min Act: -0.0001

Data Index: 1590144 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2663. Min Act: -0.0001

Data Index: 1592435 (Python Code)

Max Activating Token Index: 361

Text #10

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2378. Min Act: -0.0001

Data Index: 1439893 (Python Code)

Max Activating Token Index: 1022

Text #11

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1499461 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2165. Min Act: -0.0001

Data Index: 1640776 (Python Code)

Max Activating Token Index: 507

Text #13

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2318. Min Act: -0.0001

Data Index: 1492541 (Python Code)

Max Activating Token Index: 551

Text #14

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2363. Min Act: -0.0001

Data Index: 1535089 (Python Code)

Max Activating Token Index: 703

Text #15

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2199. Min Act: -0.0001

Data Index: 1386662 (Python Code)

Max Activating Token Index: 380

Text #16

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2369. Min Act: -0.0001

Data Index: 1621794 (Python Code)

Max Activating Token Index: 709

Text #17

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2157. Min Act: -0.0001

Data Index: 1454210 (Python Code)

Max Activating Token Index: 742

Text #18

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1620202 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2293. Min Act: -0.0001

Data Index: 1470904 (Python Code)

Max Activating Token Index: 16