Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2534 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6815. Min Act: -0.0001

Data Index: 1128147 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.7247. Min Act: -0.0001

Data Index: 446887 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6599. Min Act: -0.0001

Data Index: 257482 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6524. Min Act: -0.0001

Data Index: 1020248 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6926. Min Act: -0.0001

Data Index: 906297 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6447. Min Act: -0.0001

Data Index: 1219444 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6608. Min Act: -0.0001

Data Index: 772587 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6626. Min Act: -0.0001

Data Index: 610031 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1627869 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6337. Min Act: -0.0001

Data Index: 193560 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6165. Min Act: -0.0001

Data Index: 737614 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6269. Min Act: -0.0001

Data Index: 346033 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5936. Min Act: -0.0001

Data Index: 818583 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6229. Min Act: -0.0001

Data Index: 225372 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6210. Min Act: -0.0001

Data Index: 581465 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5989. Min Act: -0.0001

Data Index: 1240452 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5935. Min Act: -0.0001

Data Index: 1308563 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6388. Min Act: -0.0001

Data Index: 812232 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1151442 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6466. Min Act: -0.0001

Data Index: 155971 (C4 (Web Text))

Max Activating Token Index: 164