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

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

Neuron 1315 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.4169. Min Range: -10.4169

Max Act: 10.4169. Min Act: -0.0000

Data Index: 1053059 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 10.4169. Min Range: -10.4169

Max Act: 10.1808. Min Act: -0.0000

Data Index: 436965 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 10.4169. Min Range: -10.4169

Max Act: 10.1500. Min Act: -0.0000

Data Index: 144848 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 10.4169. Min Range: -10.4169

Max Act: 10.0844. Min Act: -0.0000

Data Index: 66975 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 10.4169. Min Range: -10.4169

Max Act: 9.0953. Min Act: -0.0000

Data Index: 602208 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.7729. Min Act: -0.0000

Data Index: 794957 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.6627. Min Act: -0.0000

Data Index: 800353 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.8774. Min Act: -0.0000

Data Index: 814565 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.5662. Min Act: -0.0000

Data Index: 209036 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.0425. Min Act: -0.0000

Data Index: 559085 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.4828. Min Act: -0.0000

Data Index: 952860 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.4669. Min Act: -0.0000

Data Index: 997186 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 10.4169. Min Range: -10.4169

Max Act: 7.9381. Min Act: -0.0000

Data Index: 744719 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 10.4169. Min Range: -10.4169

Max Act: 7.8983. Min Act: -0.0000

Data Index: 445040 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.1485. Min Act: -0.0000

Data Index: 636732 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 10.4169. Min Range: -10.4169

Max Act: 7.9786. Min Act: -0.0000

Data Index: 546356 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 10.4169. Min Range: -10.4169

Max Act: 7.9539. Min Act: -0.0000

Data Index: 878486 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.1215. Min Act: -0.0000

Data Index: 1262613 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.0952. Min Act: -0.0000

Data Index: 1262037 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 10.4169. Min Range: -10.4169

Max Act: 8.0867. Min Act: -0.0000

Data Index: 983611 (C4 (Web Text))

Max Activating Token Index: 277