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

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

Neuron 1183 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: 0.7519. Min Range: -0.7519

Max Act: 0.7519. Min Act: -0.0001

Data Index: 1598892 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.7242. Min Act: -0.0001

Data Index: 1536781 (Python Code)

Max Activating Token Index: 230

Text #2

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6922. Min Act: -0.0001

Data Index: 1526613 (Python Code)

Max Activating Token Index: 89

Text #3

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6712. Min Act: -0.0001

Data Index: 1497247 (Python Code)

Max Activating Token Index: 768

Text #4

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6972. Min Act: -0.0001

Data Index: 1547613 (Python Code)

Max Activating Token Index: 984

Text #5

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.7361. Min Act: -0.0001

Data Index: 1578997 (Python Code)

Max Activating Token Index: 355

Text #6

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6371. Min Act: -0.0001

Data Index: 1606632 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1418909 (Python Code)

Max Activating Token Index: 942

Text #8

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6648. Min Act: -0.0001

Data Index: 1412537 (Python Code)

Max Activating Token Index: 921

Text #9

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.7007. Min Act: -0.0001

Data Index: 1417491 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6535. Min Act: -0.0001

Data Index: 1513633 (Python Code)

Max Activating Token Index: 716

Text #11

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6260. Min Act: -0.0001

Data Index: 1495795 (Python Code)

Max Activating Token Index: 277

Text #12

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6303. Min Act: -0.0001

Data Index: 1429826 (Python Code)

Max Activating Token Index: 970

Text #13

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6627. Min Act: -0.0001

Data Index: 1654529 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6401. Min Act: -0.0001

Data Index: 1557246 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1612508 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5674. Min Act: -0.0001

Data Index: 1439616 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6216. Min Act: -0.0001

Data Index: 1652878 (Python Code)

Max Activating Token Index: 442

Text #18

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6092. Min Act: -0.0001

Data Index: 1465245 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6112. Min Act: -0.0001

Data Index: 1387843 (Python Code)

Max Activating Token Index: 954