Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1828 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1350177 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1654438 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1361095 (Python Code)

Max Activating Token Index: 627

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0001

Data Index: 535700 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1518491 (Python Code)

Max Activating Token Index: 953

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0514. Min Act: -0.0001

Data Index: 938036 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0478. Min Act: -0.0001

Data Index: 556250 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0505. Min Act: -0.0001

Data Index: 216527 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1194273 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0453. Min Act: -0.0001

Data Index: 451262 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1412460 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1222962 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1320639 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1506169 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1608097 (Python Code)

Max Activating Token Index: 400

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0519. Min Act: -0.0001

Data Index: 194408 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0440. Min Act: -0.0001

Data Index: 625430 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1534516 (Python Code)

Max Activating Token Index: 206

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1390519 (Python Code)

Max Activating Token Index: 569

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1195632 (C4 (Web Text))

Max Activating Token Index: 68