Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1472 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1627435 (Python Code)

Max Activating Token Index: 589

Text #1

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1584198 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1554905 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1514916 (Python Code)

Max Activating Token Index: 738

Text #4

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1513975 (Python Code)

Max Activating Token Index: 618

Text #5

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1360584 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1361719 (Python Code)

Max Activating Token Index: 682

Text #7

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7845. Min Act: -0.0001

Data Index: 1598493 (Python Code)

Max Activating Token Index: 672

Text #8

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1624224 (Python Code)

Max Activating Token Index: 533

Text #9

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7572. Min Act: -0.0001

Data Index: 1619561 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1510298 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6931. Min Act: -0.0001

Data Index: 1533339 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1560111 (Python Code)

Max Activating Token Index: 971

Text #13

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7293. Min Act: -0.0001

Data Index: 1449601 (Python Code)

Max Activating Token Index: 898

Text #14

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1410011 (Python Code)

Max Activating Token Index: 975

Text #15

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7163. Min Act: -0.0001

Data Index: 1447873 (Python Code)

Max Activating Token Index: 947

Text #16

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6705. Min Act: -0.0001

Data Index: 1499319 (Python Code)

Max Activating Token Index: 289

Text #17

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1473112 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6149. Min Act: -0.0001

Data Index: 1610380 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1620309 (Python Code)

Max Activating Token Index: 449