Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3159 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7541. Min Act: -0.0000

Data Index: 744288 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7372. Min Act: -0.0001

Data Index: 137434 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6870. Min Act: -0.0001

Data Index: 990523 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6765. Min Act: -0.0001

Data Index: 1343394 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6750. Min Act: -0.0001

Data Index: 1357299 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6303. Min Act: -0.0001

Data Index: 852533 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6167. Min Act: -0.0000

Data Index: 777210 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6218. Min Act: -0.0000

Data Index: 569801 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5991. Min Act: -0.0001

Data Index: 1159873 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5814. Min Act: -0.0001

Data Index: 682243 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5987. Min Act: -0.0000

Data Index: 454621 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1106228 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5697. Min Act: -0.0001

Data Index: 1178699 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6063. Min Act: -0.0001

Data Index: 1078248 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5892. Min Act: -0.0001

Data Index: 720158 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5802. Min Act: -0.0001

Data Index: 1093380 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5772. Min Act: -0.0001

Data Index: 196923 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5684. Min Act: -0.0000

Data Index: 377759 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5488. Min Act: -0.0001

Data Index: 790917 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5501. Min Act: -0.0000

Data Index: 346754 (C4 (Web Text))

Max Activating Token Index: 987