Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1081 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.5894. Min Act: -0.0001

Data Index: 372383 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.5637. Min Act: -0.0001

Data Index: 501056 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.5516. Min Act: -0.0001

Data Index: 713910 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.5507. Min Act: -0.0001

Data Index: 230117 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.3312. Min Act: -0.0001

Data Index: 326321 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2695. Min Act: -0.0001

Data Index: 122449 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2279. Min Act: -0.0001

Data Index: 135041 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2056. Min Act: -0.0001

Data Index: 261481 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2080. Min Act: -0.0001

Data Index: 1347994 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2195. Min Act: -0.0001

Data Index: 652034 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0663. Min Act: -0.0001

Data Index: 1199060 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1605. Min Act: -0.0001

Data Index: 1069590 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1256. Min Act: -0.0001

Data Index: 181534 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1879. Min Act: -0.0001

Data Index: 250617 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1815. Min Act: -0.0001

Data Index: 1191652 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1373. Min Act: -0.0001

Data Index: 642331 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1486. Min Act: -0.0001

Data Index: 309425 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0952. Min Act: -0.0001

Data Index: 746891 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1234. Min Act: -0.0001

Data Index: 1311362 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2053. Min Act: -0.0001

Data Index: 936920 (C4 (Web Text))

Max Activating Token Index: 928