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

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

Neuron 5512 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.6466. Min Act: -0.0000

Data Index: 1348810 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.8899. Min Act: -0.0000

Data Index: 84984 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.9077. Min Act: -0.0000

Data Index: 297794 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.8502. Min Act: -0.0000

Data Index: 992383 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.8745. Min Act: -0.0000

Data Index: 535965 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.7096. Min Act: -0.0000

Data Index: 1145607 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.7464. Min Act: -0.0000

Data Index: 233880 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.7185. Min Act: -0.0000

Data Index: 263235 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.5518. Min Act: -0.0000

Data Index: 1327513 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.4163. Min Act: -0.0000

Data Index: 1140975 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.3350. Min Act: -0.0000

Data Index: 304843 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.3801. Min Act: -0.0000

Data Index: 761598 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.1798. Min Act: -0.0000

Data Index: 182697 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.3000. Min Act: -0.0000

Data Index: 1267301 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.2934. Min Act: -0.0000

Data Index: 296225 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.2934. Min Act: -0.0000

Data Index: 1220885 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.2941. Min Act: -0.0000

Data Index: 842830 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.2795. Min Act: -0.0000

Data Index: 304032 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.2735. Min Act: -0.0000

Data Index: 537376 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 3.6466. Min Range: -3.6466

Max Act: 2.1186. Min Act: -0.0000

Data Index: 114545 (C4 (Web Text))

Max Activating Token Index: 986