Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 63 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0338. Min Act: -0.0006

Data Index: 743141 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0345. Min Act: -0.0006

Data Index: 368900 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0331. Min Act: -0.0006

Data Index: 946459 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0331. Min Act: -0.0006

Data Index: 1199514 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0323. Min Act: -0.0006

Data Index: 922629 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0314. Min Act: -0.0006

Data Index: 671104 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0325. Min Act: -0.0006

Data Index: 637790 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0315. Min Act: -0.0006

Data Index: 150086 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0316. Min Act: -0.0006

Data Index: 717807 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0321. Min Act: -0.0006

Data Index: 395085 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0329. Min Act: -0.0006

Data Index: 587425 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0319. Min Act: -0.0006

Data Index: 640085 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0320. Min Act: -0.0006

Data Index: 808391 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1039687 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0289. Min Act: -0.0006

Data Index: 978715 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0318. Min Act: -0.0006

Data Index: 3435 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0325. Min Act: -0.0006

Data Index: 1117579 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0305. Min Act: -0.0006

Data Index: 622768 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0311. Min Act: -0.0006

Data Index: 385232 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0304. Min Act: -0.0006

Data Index: 861549 (C4 (Web Text))

Max Activating Token Index: 771