Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5796 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.5764. Min Act: -0.0001

Data Index: 366991 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 4.2032. Min Range: -4.2032

Max Act: 4.2032. Min Act: -0.0000

Data Index: 586399 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.2899. Min Act: -0.0000

Data Index: 310436 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.7354. Min Act: -0.0001

Data Index: 1018528 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.0805. Min Act: -0.0000

Data Index: 785318 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.1642. Min Act: -0.0001

Data Index: 154965 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.4769. Min Act: -0.0001

Data Index: 908939 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.1447. Min Act: -0.0000

Data Index: 213770 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.1203. Min Act: -0.0000

Data Index: 898565 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.8673. Min Act: -0.0001

Data Index: 140266 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.6346. Min Act: -0.0000

Data Index: 1107727 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.1777. Min Act: -0.0001

Data Index: 894459 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.0454. Min Act: -0.0001

Data Index: 1283791 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.5929. Min Act: -0.0000

Data Index: 1297945 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.4561. Min Act: -0.0000

Data Index: 1168038 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.6798. Min Act: -0.0000

Data Index: 1357339 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.4611. Min Act: -0.0000

Data Index: 585715 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.5291. Min Act: -0.0000

Data Index: 1286526 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.1964. Min Act: -0.0000

Data Index: 701196 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.4944. Min Act: -0.0000

Data Index: 65421 (C4 (Web Text))

Max Activating Token Index: 451