Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5646 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1189. Min Range: -3.1189

Max Act: 3.1189. Min Act: -0.0000

Data Index: 389652 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 3.1189. Min Range: -3.1189

Max Act: 2.1902. Min Act: -0.0000

Data Index: 222754 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 3.1189. Min Range: -3.1189

Max Act: 2.2953. Min Act: -0.0000

Data Index: 405027 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 3.1189. Min Range: -3.1189

Max Act: 2.2235. Min Act: -0.0000

Data Index: 19226 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 3.1189. Min Range: -3.1189

Max Act: 2.3382. Min Act: -0.0000

Data Index: 618275 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.9017. Min Act: -0.0000

Data Index: 611600 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 3.1189. Min Range: -3.1189

Max Act: 2.2185. Min Act: -0.0000

Data Index: 1276408 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 3.1189. Min Range: -3.1189

Max Act: 2.2090. Min Act: -0.0000

Data Index: 565280 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.8220. Min Act: -0.0000

Data Index: 379174 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 3.1189. Min Range: -3.1189

Max Act: 2.0097. Min Act: -0.0000

Data Index: 103109 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.8678. Min Act: -0.0000

Data Index: 739439 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.9312. Min Act: -0.0000

Data Index: 1147536 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.8240. Min Act: -0.0000

Data Index: 1176822 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 3.1189. Min Range: -3.1189

Max Act: 2.0237. Min Act: -0.0000

Data Index: 1012561 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.8397. Min Act: -0.0000

Data Index: 517747 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.7902. Min Act: -0.0000

Data Index: 887116 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1148343 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.9292. Min Act: -0.0000

Data Index: 59929 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.6529. Min Act: -0.0000

Data Index: 143026 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 3.1189. Min Range: -3.1189

Max Act: 1.8050. Min Act: -0.0000

Data Index: 752732 (C4 (Web Text))

Max Activating Token Index: 613