Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4603 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.8643. Min Act: -0.0000

Data Index: 970873 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.8748. Min Act: -0.0000

Data Index: 372368 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7791. Min Act: -0.0000

Data Index: 147598 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7608. Min Act: -0.0000

Data Index: 523634 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7363. Min Act: -0.0000

Data Index: 875368 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1238656 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1016696 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6980. Min Act: -0.0000

Data Index: 997755 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6763. Min Act: -0.0000

Data Index: 123181 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6861. Min Act: -0.0000

Data Index: 411439 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6864. Min Act: -0.0000

Data Index: 31614 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6442. Min Act: -0.0000

Data Index: 496155 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.7022. Min Act: -0.0000

Data Index: 182621 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6315. Min Act: -0.0000

Data Index: 710919 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1091173 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1216859 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6289. Min Act: -0.0000

Data Index: 433259 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1257553 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1254441 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.8748. Min Range: -0.8748

Max Act: 0.6189. Min Act: -0.0000

Data Index: 116080 (C4 (Web Text))

Max Activating Token Index: 616