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

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

Neuron 289 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1460. Min Act: -0.0001

Data Index: 353921 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1229920 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1309147 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1135. Min Act: -0.0001

Data Index: 451875 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1135. Min Act: -0.0001

Data Index: 734995 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1157. Min Act: -0.0001

Data Index: 530444 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1340103 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1007140 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1075. Min Act: -0.0001

Data Index: 121103 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0996. Min Act: -0.0001

Data Index: 843216 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1084. Min Act: -0.0001

Data Index: 848766 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1384460 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1009. Min Act: -0.0001

Data Index: 928517 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1639265 (Python Code)

Max Activating Token Index: 970

Text #14

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1019. Min Act: -0.0001

Data Index: 625333 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1258641 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1002376 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1548843 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0910. Min Act: -0.0001

Data Index: 78417 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1041. Min Act: -0.0001

Data Index: 183434 (C4 (Web Text))

Max Activating Token Index: 187