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

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

Neuron 932 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4101. Min Range: -2.4101

Max Act: 2.4101. Min Act: -0.0000

Data Index: 91567 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 2.4101. Min Range: -2.4101

Max Act: 2.0749. Min Act: -0.0000

Data Index: 168446 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.9626. Min Act: -0.0000

Data Index: 456542 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 2.4101. Min Range: -2.4101

Max Act: 2.0537. Min Act: -0.0000

Data Index: 969727 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.8933. Min Act: -0.0000

Data Index: 767892 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.8810. Min Act: -0.0000

Data Index: 604887 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.7265. Min Act: -0.0000

Data Index: 555221 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.7743. Min Act: -0.0000

Data Index: 1244113 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.8393. Min Act: 0.0000

Data Index: 991248 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.7239. Min Act: -0.0000

Data Index: 307636 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.7092. Min Act: -0.0000

Data Index: 730415 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.7102. Min Act: -0.0000

Data Index: 1047684 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.7000. Min Act: -0.0000

Data Index: 646050 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.6836. Min Act: -0.0000

Data Index: 987737 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.6782. Min Act: -0.0000

Data Index: 563510 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.6546. Min Act: -0.0000

Data Index: 892598 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.5552. Min Act: -0.0000

Data Index: 1226394 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.6456. Min Act: -0.0000

Data Index: 678612 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.6282. Min Act: -0.0000

Data Index: 782687 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.6257. Min Act: 0.0000

Data Index: 604679 (C4 (Web Text))

Max Activating Token Index: 752