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

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

Neuron 1235 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0768. Min Range: -2.0768

Max Act: 2.0059. Min Act: -0.0000

Data Index: 240045 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.8673. Min Act: -0.0000

Data Index: 873176 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 2.0768. Min Range: -2.0768

Max Act: 2.0768. Min Act: -0.0000

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.7684. Min Act: -0.0000

Data Index: 548975 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.7809. Min Act: -0.0000

Data Index: 511001 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.7225. Min Act: -0.0000

Data Index: 574610 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.6859. Min Act: -0.0000

Data Index: 497843 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.7045. Min Act: -0.0000

Data Index: 158375 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.6834. Min Act: -0.0000

Data Index: 347565 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.6645. Min Act: -0.0000

Data Index: 454827 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.6610. Min Act: -0.0000

Data Index: 1257764 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.6027. Min Act: -0.0000

Data Index: 911748 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5561. Min Act: -0.0000

Data Index: 867296 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5997. Min Act: -0.0000

Data Index: 930243 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5865. Min Act: -0.0000

Data Index: 126080 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5339. Min Act: -0.0000

Data Index: 536084 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.4962. Min Act: -0.0000

Data Index: 731424 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5818. Min Act: -0.0000

Data Index: 936412 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5334. Min Act: -0.0000

Data Index: 1026112 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.4042. Min Act: -0.0001

Data Index: 413816 (C4 (Web Text))

Max Activating Token Index: 309