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

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

Neuron 3806 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3539. Min Range: -2.3539

Max Act: 2.3539. Min Act: -0.0000

Data Index: 896110 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 2.3539. Min Range: -2.3539

Max Act: 2.3501. Min Act: 0.0000

Data Index: 1296192 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 2.3539. Min Range: -2.3539

Max Act: 2.1605. Min Act: -0.0000

Data Index: 107649 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.9988. Min Act: 0.0001

Data Index: 1149460 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 2.3539. Min Range: -2.3539

Max Act: 2.0123. Min Act: -0.0000

Data Index: 1016943 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 2.3539. Min Range: -2.3539

Max Act: 2.0228. Min Act: -0.0000

Data Index: 1023317 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.6755. Min Act: -0.0000

Data Index: 230588 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1119510 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.6590. Min Act: -0.0000

Data Index: 52312 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.7451. Min Act: -0.0000

Data Index: 127002 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1225318 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.7972. Min Act: -0.0000

Data Index: 162992 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.5938. Min Act: -0.0000

Data Index: 721325 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.6815. Min Act: -0.0000

Data Index: 627312 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.6822. Min Act: -0.0000

Data Index: 193763 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.5695. Min Act: -0.0000

Data Index: 715894 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.7572. Min Act: -0.0000

Data Index: 648219 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.6168. Min Act: -0.0000

Data Index: 291078 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.5095. Min Act: -0.0000

Data Index: 1055206 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 2.3539. Min Range: -2.3539

Max Act: 1.6298. Min Act: -0.0000

Data Index: 1145802 (C4 (Web Text))

Max Activating Token Index: 103