Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2768 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0968. Min Act: -0.0001

Data Index: 1397828 (Python Code)

Max Activating Token Index: 110

Text #1

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.8897. Min Act: -0.0001

Data Index: 1640824 (Python Code)

Max Activating Token Index: 56

Text #2

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.7765. Min Act: -0.0001

Data Index: 1603282 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.7611. Min Act: -0.0001

Data Index: 1400344 (Python Code)

Max Activating Token Index: 434

Text #4

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.7965. Min Act: -0.0001

Data Index: 1485022 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.8352. Min Act: -0.0001

Data Index: 1376230 (Python Code)

Max Activating Token Index: 881

Text #6

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1639456 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6676. Min Act: -0.0001

Data Index: 1636704 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6570. Min Act: -0.0001

Data Index: 1552903 (Python Code)

Max Activating Token Index: 170

Text #9

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6889. Min Act: -0.0001

Data Index: 1634506 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6731. Min Act: -0.0001

Data Index: 1548393 (Python Code)

Max Activating Token Index: 540

Text #11

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.7115. Min Act: -0.0001

Data Index: 1549129 (Python Code)

Max Activating Token Index: 682

Text #12

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6527. Min Act: -0.0001

Data Index: 1387949 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6441. Min Act: -0.0001

Data Index: 1577146 (Python Code)

Max Activating Token Index: 467

Text #14

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6070. Min Act: -0.0001

Data Index: 1601016 (Python Code)

Max Activating Token Index: 288

Text #15

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6460. Min Act: -0.0001

Data Index: 1397474 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6627. Min Act: -0.0001

Data Index: 1448497 (Python Code)

Max Activating Token Index: 443

Text #17

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6430. Min Act: -0.0001

Data Index: 1363573 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.6378. Min Act: -0.0001

Data Index: 1464827 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.5990. Min Act: -0.0001

Data Index: 1438448 (Python Code)

Max Activating Token Index: 604