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

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

Neuron 1718 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4394. Min Act: -0.0001

Data Index: 273361 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4772. Min Act: -0.0001

Data Index: 1154967 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4591. Min Act: -0.0001

Data Index: 757395 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4233. Min Act: -0.0001

Data Index: 283311 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4374. Min Act: -0.0001

Data Index: 662248 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4701. Min Act: -0.0001

Data Index: 1025677 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4369. Min Act: -0.0001

Data Index: 18890 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4445. Min Act: -0.0001

Data Index: 1181031 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4284. Min Act: -0.0001

Data Index: 978236 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4093. Min Act: -0.0001

Data Index: 89547 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4145. Min Act: -0.0000

Data Index: 565237 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3960. Min Act: -0.0001

Data Index: 746568 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3927. Min Act: -0.0001

Data Index: 1040888 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4363. Min Act: -0.0001

Data Index: 560618 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4107. Min Act: -0.0001

Data Index: 414909 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4322. Min Act: -0.0000

Data Index: 165525 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4066. Min Act: -0.0001

Data Index: 1349014 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3755. Min Act: -0.0001

Data Index: 1101854 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3694. Min Act: -0.0001

Data Index: 142090 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3831. Min Act: -0.0001

Data Index: 538455 (C4 (Web Text))

Max Activating Token Index: 580