Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 970 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2571. Min Act: -0.0001

Data Index: 503661 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2544. Min Act: -0.0001

Data Index: 1329075 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2529. Min Act: -0.0001

Data Index: 919553 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2403. Min Act: -0.0001

Data Index: 207470 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2498. Min Act: -0.0001

Data Index: 844778 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2498. Min Act: -0.0001

Data Index: 1298828 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2392. Min Act: -0.0001

Data Index: 290828 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1118503 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2435. Min Act: -0.0001

Data Index: 87608 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2246. Min Act: -0.0001

Data Index: 583699 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2483. Min Act: -0.0001

Data Index: 267113 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2484. Min Act: -0.0001

Data Index: 267212 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2230. Min Act: -0.0001

Data Index: 546232 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2366. Min Act: -0.0001

Data Index: 1104569 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2018. Min Act: -0.0001

Data Index: 1040029 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2271. Min Act: -0.0001

Data Index: 518890 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2408. Min Act: -0.0002

Data Index: 504336 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1232554 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1039174 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2367. Min Act: -0.0001

Data Index: 687130 (C4 (Web Text))

Max Activating Token Index: 415