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

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

Neuron 5044 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.5098. Min Act: -0.0000

Data Index: 369890 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.5469. Min Act: -0.0000

Data Index: 397975 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.5029. Min Act: -0.0000

Data Index: 126039 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.3508. Min Act: -0.0000

Data Index: 666689 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.3579. Min Act: -0.0000

Data Index: 909334 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.3122. Min Act: -0.0000

Data Index: 675685 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.4286. Min Act: -0.0000

Data Index: 83822 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.2745. Min Act: -0.0000

Data Index: 304899 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.2416. Min Act: -0.0000

Data Index: 616209 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.2108. Min Act: -0.0000

Data Index: 191375 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1059568 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.2177. Min Act: -0.0000

Data Index: 284873 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.2504. Min Act: -0.0000

Data Index: 144534 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.2524. Min Act: -0.0000

Data Index: 43146 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.2465. Min Act: -0.0000

Data Index: 669572 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1394092 (Python Code)

Max Activating Token Index: 255

Text #16

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.1403. Min Act: -0.0000

Data Index: 809192 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.1901. Min Act: -0.0000

Data Index: 957000 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1056243 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 1.5469. Min Range: -1.5469

Max Act: 1.2360. Min Act: -0.0000

Data Index: 151354 (C4 (Web Text))

Max Activating Token Index: 626