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

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

Neuron 1512 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0610. Min Range: -8.0610

Max Act: 8.0610. Min Act: -0.0000

Data Index: 238355 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 8.0610. Min Range: -8.0610

Max Act: 7.2485. Min Act: -0.0000

Data Index: 1017545 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.8393. Min Act: -0.0000

Data Index: 815780 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 8.0610. Min Range: -8.0610

Max Act: 7.0679. Min Act: -0.0000

Data Index: 140489 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 8.0610. Min Range: -8.0610

Max Act: 7.0348. Min Act: -0.0000

Data Index: 251632 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.8027. Min Act: -0.0000

Data Index: 32190 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.8394. Min Act: -0.0000

Data Index: 1200792 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.5473. Min Act: -0.0000

Data Index: 217479 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.4375. Min Act: -0.0000

Data Index: 1087252 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.4680. Min Act: -0.0000

Data Index: 433379 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.6105. Min Act: -0.0000

Data Index: 60117 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.4386. Min Act: -0.0000

Data Index: 1317334 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.4823. Min Act: -0.0000

Data Index: 118351 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.4776. Min Act: -0.0000

Data Index: 1079056 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.2808. Min Act: -0.0000

Data Index: 410065 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.0921. Min Act: -0.0000

Data Index: 1082646 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.4295. Min Act: -0.0000

Data Index: 236918 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.1988. Min Act: -0.0000

Data Index: 575854 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.1672. Min Act: -0.0000

Data Index: 935325 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 8.0610. Min Range: -8.0610

Max Act: 6.3099. Min Act: -0.0000

Data Index: 131688 (C4 (Web Text))

Max Activating Token Index: 402