Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1109 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.9990. Min Act: -0.0001

Data Index: 601332 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.3973. Min Act: -0.0001

Data Index: 234363 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.4671. Min Act: -0.0001

Data Index: 1189218 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.3215. Min Act: -0.0001

Data Index: 640994 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.2917. Min Act: -0.0001

Data Index: 1180525 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.1979. Min Act: -0.0001

Data Index: 295597 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.1913. Min Act: -0.0001

Data Index: 939726 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.1365. Min Act: -0.0001

Data Index: 432842 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.1767. Min Act: -0.0001

Data Index: 71161 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.9990. Min Range: -1.9990

Max Act: 0.9961. Min Act: -0.0001

Data Index: 736887 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.0758. Min Act: -0.0001

Data Index: 920794 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.0720. Min Act: -0.0001

Data Index: 791759 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.9990. Min Range: -1.9990

Max Act: 0.9928. Min Act: -0.0001

Data Index: 1225940 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 1.9990. Min Range: -1.9990

Max Act: 0.9348. Min Act: -0.0001

Data Index: 694865 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.0812. Min Act: -0.0001

Data Index: 422008 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.0793. Min Act: -0.0001

Data Index: 1185638 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.1466. Min Act: -0.0001

Data Index: 331328 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.9990. Min Range: -1.9990

Max Act: 0.9835. Min Act: -0.0001

Data Index: 1291924 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.1407. Min Act: -0.0001

Data Index: 969506 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 1.9990. Min Range: -1.9990

Max Act: 1.1267. Min Act: -0.0001

Data Index: 1100649 (C4 (Web Text))

Max Activating Token Index: 80