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

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

Neuron 3813 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.8806. Min Act: -0.0000

Data Index: 1264585 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.7848. Min Act: -0.0000

Data Index: 447958 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.8648. Min Act: -0.0000

Data Index: 876968 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 2.1244. Min Range: -2.1244

Max Act: 2.1244. Min Act: -0.0000

Data Index: 246055 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.8199. Min Act: -0.0000

Data Index: 1128470 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.9878. Min Act: -0.0000

Data Index: 1308591 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.6413. Min Act: -0.0000

Data Index: 1150722 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.5349. Min Act: -0.0000

Data Index: 86937 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.4536. Min Act: -0.0000

Data Index: 1058507 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.6678. Min Act: -0.0000

Data Index: 409701 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.5125. Min Act: -0.0000

Data Index: 75922 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.4661. Min Act: -0.0000

Data Index: 1270052 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.6140. Min Act: -0.0000

Data Index: 270748 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.5416. Min Act: -0.0000

Data Index: 579906 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.7373. Min Act: -0.0000

Data Index: 1181419 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.6003. Min Act: -0.0000

Data Index: 917569 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.5074. Min Act: -0.0000

Data Index: 61283 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.4653. Min Act: -0.0000

Data Index: 322052 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.3543. Min Act: -0.0000

Data Index: 151287 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 2.1244. Min Range: -2.1244

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1225252 (C4 (Web Text))

Max Activating Token Index: 584