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

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

Neuron 421 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: 1.0270. Min Range: -1.0270

Max Act: 1.0270. Min Act: -0.0000

Data Index: 111267 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9672. Min Act: -0.0000

Data Index: 537835 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8289. Min Act: 0.0000

Data Index: 321872 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7698. Min Act: 0.0001

Data Index: 600660 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7437. Min Act: -0.0000

Data Index: 186026 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7417. Min Act: -0.0000

Data Index: 786620 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7791. Min Act: 0.0000

Data Index: 4699 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7150. Min Act: 0.0000

Data Index: 717417 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7263. Min Act: -0.0000

Data Index: 309709 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6924. Min Act: 0.0000

Data Index: 1094074 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7329. Min Act: 0.0000

Data Index: 1259984 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7064. Min Act: -0.0000

Data Index: 179547 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7088. Min Act: -0.0000

Data Index: 365910 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6822. Min Act: -0.0000

Data Index: 86087 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7086. Min Act: 0.0000

Data Index: 382233 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6647. Min Act: -0.0000

Data Index: 422107 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6786. Min Act: 0.0001

Data Index: 57981 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6726. Min Act: -0.0000

Data Index: 212895 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6696. Min Act: -0.0000

Data Index: 783720 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6662. Min Act: -0.0000

Data Index: 701311 (C4 (Web Text))

Max Activating Token Index: 1018