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

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

Neuron 3176 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2386. Min Range: -1.2386

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1403686 (Python Code)

Max Activating Token Index: 610

Text #1

Max Range: 1.2386. Min Range: -1.2386

Max Act: 1.0167. Min Act: -0.0000

Data Index: 602455 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1100581 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1393638 (Python Code)

Max Activating Token Index: 108

Text #4

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7851. Min Act: -0.0000

Data Index: 807991 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1325167 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7735. Min Act: -0.0000

Data Index: 625362 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7327. Min Act: -0.0000

Data Index: 911930 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7521. Min Act: -0.0000

Data Index: 169290 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1027858 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7700. Min Act: -0.0000

Data Index: 350642 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7366. Min Act: 0.0000

Data Index: 1376830 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7063. Min Act: -0.0000

Data Index: 409783 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1188214 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7441. Min Act: -0.0000

Data Index: 691450 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.6849. Min Act: -0.0000

Data Index: 657168 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1291880 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7210. Min Act: -0.0000

Data Index: 2303 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.7170. Min Act: -0.0000

Data Index: 278638 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 1.2386. Min Range: -1.2386

Max Act: 0.6759. Min Act: -0.0000

Data Index: 216683 (C4 (Web Text))

Max Activating Token Index: 115