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

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

Neuron 5763 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.5520. Min Act: -0.0001

Data Index: 554005 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.3199. Min Act: -0.0001

Data Index: 1063997 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.4803. Min Act: -0.0001

Data Index: 1212963 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.3208. Min Act: -0.0001

Data Index: 303944 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.2881. Min Act: -0.0001

Data Index: 529885 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1970. Min Act: -0.0001

Data Index: 150420 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.2748. Min Act: -0.0001

Data Index: 491275 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.2718. Min Act: -0.0001

Data Index: 937240 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.2268. Min Act: -0.0001

Data Index: 950225 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1370. Min Act: -0.0001

Data Index: 17920 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1141. Min Act: -0.0001

Data Index: 1212770 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1924. Min Act: -0.0001

Data Index: 655435 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1318. Min Act: -0.0001

Data Index: 733102 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.2569. Min Act: -0.0001

Data Index: 145714 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.2909. Min Act: -0.0001

Data Index: 144880 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1823. Min Act: -0.0001

Data Index: 789380 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.2425. Min Act: -0.0001

Data Index: 1168872 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1857. Min Act: -0.0001

Data Index: 907414 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1862. Min Act: -0.0001

Data Index: 1280291 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1353. Min Act: -0.0001

Data Index: 270541 (C4 (Web Text))

Max Activating Token Index: 659