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

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

Neuron 1467 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7881. Min Act: -0.0003

Data Index: 984635 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7112. Min Act: -0.0003

Data Index: 1375377 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6533. Min Act: -0.0003

Data Index: 1295006 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6379. Min Act: -0.0003

Data Index: 1430285 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6494. Min Act: -0.0003

Data Index: 1465094 (Python Code)

Max Activating Token Index: 1021

Text #5

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6764. Min Act: -0.0003

Data Index: 329557 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6582. Min Act: -0.0003

Data Index: 1144984 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6204. Min Act: -0.0003

Data Index: 1409321 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5619. Min Act: -0.0003

Data Index: 1381646 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6547. Min Act: -0.0003

Data Index: 122339 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6089. Min Act: -0.0003

Data Index: 1402709 (Python Code)

Max Activating Token Index: 428

Text #11

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6239. Min Act: -0.0003

Data Index: 541499 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6295. Min Act: -0.0003

Data Index: 970926 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6174. Min Act: -0.0003

Data Index: 1475273 (Python Code)

Max Activating Token Index: 956

Text #14

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6205. Min Act: -0.0003

Data Index: 680086 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6463. Min Act: -0.0003

Data Index: 1473289 (Python Code)

Max Activating Token Index: 133

Text #16

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6084. Min Act: -0.0003

Data Index: 153581 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6206. Min Act: -0.0003

Data Index: 1181319 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6287. Min Act: -0.0003

Data Index: 1640912 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5525. Min Act: -0.0003

Data Index: 1647646 (Python Code)

Max Activating Token Index: 328