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

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

Neuron 3380 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8311. Min Act: -0.0001

Data Index: 660947 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7633. Min Act: -0.0001

Data Index: 322487 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7805. Min Act: -0.0001

Data Index: 734708 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6895. Min Act: -0.0001

Data Index: 465757 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6771. Min Act: -0.0001

Data Index: 470348 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5814. Min Act: -0.0001

Data Index: 179782 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6761. Min Act: -0.0001

Data Index: 518716 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6094. Min Act: -0.0001

Data Index: 567314 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7051. Min Act: -0.0001

Data Index: 1259011 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5934. Min Act: -0.0001

Data Index: 959947 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6122. Min Act: -0.0001

Data Index: 1155504 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1030271 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6288. Min Act: -0.0001

Data Index: 815875 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6062. Min Act: -0.0001

Data Index: 392189 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5971. Min Act: -0.0001

Data Index: 372315 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5674. Min Act: -0.0001

Data Index: 504620 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5872. Min Act: -0.0001

Data Index: 456385 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5407. Min Act: -0.0001

Data Index: 745536 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5762. Min Act: -0.0001

Data Index: 280422 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5755. Min Act: -0.0001

Data Index: 218933 (C4 (Web Text))

Max Activating Token Index: 121