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

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

Neuron 4781 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3849. Min Act: -0.0000

Data Index: 704456 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.4658. Min Act: -0.0000

Data Index: 71480 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3843. Min Act: -0.0000

Data Index: 678957 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3606. Min Act: -0.0000

Data Index: 188890 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3871. Min Act: -0.0000

Data Index: 4711 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.4077. Min Act: -0.0000

Data Index: 436444 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3144. Min Act: -0.0000

Data Index: 504458 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3782. Min Act: -0.0000

Data Index: 548805 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3144. Min Act: -0.0000

Data Index: 874367 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3238. Min Act: -0.0000

Data Index: 3876 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1344803 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3234. Min Act: -0.0000

Data Index: 590997 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3435. Min Act: -0.0000

Data Index: 853474 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3183. Min Act: -0.0000

Data Index: 270689 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3318. Min Act: -0.0000

Data Index: 997091 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3252. Min Act: -0.0000

Data Index: 882960 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3048. Min Act: -0.0000

Data Index: 577770 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3014. Min Act: -0.0000

Data Index: 286634 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2980. Min Act: -0.0000

Data Index: 736894 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2964. Min Act: -0.0000

Data Index: 928689 (C4 (Web Text))

Max Activating Token Index: 740