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

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

Neuron 898 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9709. Min Act: -0.0001

Data Index: 833001 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.7043. Min Act: -0.0000

Data Index: 390007 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.4944. Min Act: -0.0001

Data Index: 262442 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.5032. Min Act: -0.0000

Data Index: 1243956 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.4492. Min Act: -0.0001

Data Index: 351686 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.4424. Min Act: -0.0001

Data Index: 279722 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.4306. Min Act: -0.0001

Data Index: 1505014 (Python Code)

Max Activating Token Index: 867

Text #7

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.3417. Min Act: -0.0001

Data Index: 610064 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.4069. Min Act: -0.0001

Data Index: 1059845 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2983. Min Act: -0.0000

Data Index: 227622 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.3369. Min Act: -0.0001

Data Index: 956479 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.3169. Min Act: -0.0001

Data Index: 1111715 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2948. Min Act: -0.0001

Data Index: 328327 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2951. Min Act: -0.0001

Data Index: 1183283 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2863. Min Act: -0.0001

Data Index: 63378 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2832. Min Act: -0.0000

Data Index: 828234 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2778. Min Act: -0.0001

Data Index: 951825 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2588. Min Act: -0.0001

Data Index: 705376 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.1810. Min Act: -0.0000

Data Index: 885456 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2530. Min Act: -0.0000

Data Index: 145612 (C4 (Web Text))

Max Activating Token Index: 368