Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3674 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.4539. Min Act: -0.0002

Data Index: 144804 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.4576. Min Act: -0.0002

Data Index: 902274 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.4107. Min Act: -0.0002

Data Index: 700201 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.4235. Min Act: -0.0002

Data Index: 1165695 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.4289. Min Act: -0.0002

Data Index: 826395 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3539. Min Act: -0.0002

Data Index: 588599 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3731. Min Act: -0.0002

Data Index: 281804 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3875. Min Act: -0.0002

Data Index: 1044931 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3586. Min Act: -0.0002

Data Index: 1027920 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3583. Min Act: -0.0002

Data Index: 539843 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3686. Min Act: -0.0002

Data Index: 677116 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.4143. Min Act: -0.0002

Data Index: 1237485 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3779. Min Act: -0.0002

Data Index: 1197662 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3400. Min Act: -0.0002

Data Index: 57668 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3712. Min Act: -0.0002

Data Index: 1349874 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3459. Min Act: -0.0002

Data Index: 307976 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3427. Min Act: -0.0002

Data Index: 1230300 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3268. Min Act: -0.0002

Data Index: 1192565 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3485. Min Act: -0.0002

Data Index: 473793 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3552. Min Act: -0.0002

Data Index: 359116 (C4 (Web Text))

Max Activating Token Index: 136