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

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

Neuron 1080 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0004

Data Index: 1396694 (Python Code)

Max Activating Token Index: 246

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0543. Min Act: -0.0004

Data Index: 1392648 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0505. Min Act: -0.0004

Data Index: 1626756 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0479. Min Act: -0.0004

Data Index: 1390518 (Python Code)

Max Activating Token Index: 135

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0500. Min Act: -0.0004

Data Index: 1379304 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0455. Min Act: -0.0004

Data Index: 1614344 (Python Code)

Max Activating Token Index: 1003

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0531. Min Act: -0.0004

Data Index: 1406492 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0482. Min Act: -0.0004

Data Index: 1487222 (Python Code)

Max Activating Token Index: 886

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0441. Min Act: -0.0004

Data Index: 1452413 (Python Code)

Max Activating Token Index: 186

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0467. Min Act: -0.0004

Data Index: 1566816 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0506. Min Act: -0.0004

Data Index: 1617889 (Python Code)

Max Activating Token Index: 718

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0474. Min Act: -0.0004

Data Index: 1443299 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0466. Min Act: -0.0004

Data Index: 1404043 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0454. Min Act: -0.0004

Data Index: 1618992 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0436. Min Act: -0.0004

Data Index: 1505413 (Python Code)

Max Activating Token Index: 1003

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0457. Min Act: -0.0004

Data Index: 1573507 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0419. Min Act: -0.0004

Data Index: 1632738 (Python Code)

Max Activating Token Index: 775

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0395. Min Act: -0.0004

Data Index: 1635836 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1544314 (Python Code)

Max Activating Token Index: 585

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0466. Min Act: -0.0004

Data Index: 1642499 (Python Code)

Max Activating Token Index: 400