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

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

Neuron 40 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: 0.9641. Min Range: -0.9641

Max Act: 0.9641. Min Act: -0.0001

Data Index: 501682 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7408. Min Act: -0.0001

Data Index: 905919 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7837. Min Act: -0.0001

Data Index: 1090312 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7108. Min Act: -0.0001

Data Index: 302168 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6623. Min Act: -0.0001

Data Index: 771063 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1030888 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6255. Min Act: -0.0001

Data Index: 97434 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5714. Min Act: -0.0001

Data Index: 1521872 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6374. Min Act: -0.0001

Data Index: 665581 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6519. Min Act: -0.0001

Data Index: 336679 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6305. Min Act: -0.0001

Data Index: 1052928 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6504. Min Act: -0.0001

Data Index: 546686 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6466. Min Act: -0.0001

Data Index: 647168 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6680. Min Act: -0.0001

Data Index: 71133 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1126347 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6184. Min Act: -0.0001

Data Index: 508128 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6016. Min Act: -0.0001

Data Index: 1008761 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6170. Min Act: -0.0001

Data Index: 1105858 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6398. Min Act: -0.0001

Data Index: 610702 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6805. Min Act: -0.0001

Data Index: 11319 (C4 (Web Text))

Max Activating Token Index: 907