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

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

Neuron 1878 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3339. Min Act: -0.0001

Data Index: 294589 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3433. Min Act: -0.0001

Data Index: 394324 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2933. Min Act: -0.0001

Data Index: 942510 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1001629 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2813. Min Act: -0.0001

Data Index: 609447 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2642. Min Act: -0.0001

Data Index: 176374 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2471. Min Act: -0.0001

Data Index: 130130 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2419. Min Act: -0.0001

Data Index: 424393 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2315. Min Act: -0.0001

Data Index: 784927 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1280697 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2353. Min Act: -0.0001

Data Index: 85669 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2355. Min Act: -0.0001

Data Index: 489316 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2324. Min Act: -0.0001

Data Index: 948410 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2405. Min Act: -0.0001

Data Index: 936074 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2300. Min Act: -0.0001

Data Index: 620954 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2216. Min Act: -0.0001

Data Index: 609546 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.1950. Min Act: -0.0001

Data Index: 539691 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2204. Min Act: -0.0001

Data Index: 686095 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2209. Min Act: -0.0001

Data Index: 1311670 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2201. Min Act: -0.0001

Data Index: 597173 (C4 (Web Text))

Max Activating Token Index: 950