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

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

Neuron 3715 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6745. Min Act: -0.0001

Data Index: 1093733 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6958. Min Act: -0.0001

Data Index: 95095 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6177. Min Act: -0.0001

Data Index: 215919 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5737. Min Act: -0.0001

Data Index: 1223354 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5977. Min Act: -0.0001

Data Index: 98469 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5702. Min Act: -0.0001

Data Index: 1000392 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5679. Min Act: -0.0001

Data Index: 10466 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5468. Min Act: -0.0001

Data Index: 38869 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5512. Min Act: -0.0001

Data Index: 231978 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5472. Min Act: -0.0001

Data Index: 650623 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5291. Min Act: -0.0001

Data Index: 254976 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5146. Min Act: -0.0001

Data Index: 953144 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.4637. Min Act: -0.0001

Data Index: 459421 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5097. Min Act: -0.0001

Data Index: 743301 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.4628. Min Act: -0.0001

Data Index: 1071369 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.4890. Min Act: -0.0001

Data Index: 352916 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.4569. Min Act: -0.0001

Data Index: 709173 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.4873. Min Act: -0.0001

Data Index: 206720 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5020. Min Act: -0.0001

Data Index: 292518 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5163. Min Act: -0.0001

Data Index: 391425 (C4 (Web Text))

Max Activating Token Index: 984