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

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

Neuron 3792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.8091. Min Act: -0.0000

Data Index: 340181 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.6218. Min Act: -0.0000

Data Index: 921451 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.6087. Min Act: -0.0000

Data Index: 747296 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.6451. Min Act: -0.0000

Data Index: 653272 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.4768. Min Act: -0.0000

Data Index: 174622 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.2308. Min Act: -0.0000

Data Index: 328181 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.1665. Min Act: -0.0000

Data Index: 1325662 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.1147. Min Act: -0.0000

Data Index: 241220 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.9921. Min Act: -0.0000

Data Index: 833338 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.9780. Min Act: -0.0000

Data Index: 306785 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.0256. Min Act: -0.0000

Data Index: 436059 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.9973. Min Act: -0.0000

Data Index: 1325915 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.8956. Min Act: -0.0000

Data Index: 37804 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.0167. Min Act: -0.0000

Data Index: 853873 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.8630. Min Act: -0.0000

Data Index: 432509 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.9648. Min Act: -0.0000

Data Index: 877259 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.9660. Min Act: -0.0000

Data Index: 508539 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.9278. Min Act: -0.0000

Data Index: 740844 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.8959. Min Act: -0.0000

Data Index: 39712 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.7893. Min Act: -0.0000

Data Index: 131030 (C4 (Web Text))

Max Activating Token Index: 736