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

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

Neuron 849 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2581. Min Act: -0.0001

Data Index: 104261 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2554. Min Act: -0.0001

Data Index: 41242 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2467. Min Act: -0.0001

Data Index: 519676 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2576. Min Act: -0.0001

Data Index: 967219 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2414. Min Act: -0.0000

Data Index: 133383 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2295. Min Act: -0.0001

Data Index: 161822 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2425. Min Act: -0.0001

Data Index: 87022 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2328. Min Act: -0.0000

Data Index: 197375 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2308. Min Act: -0.0001

Data Index: 725557 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2285. Min Act: -0.0001

Data Index: 991042 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2166. Min Act: -0.0001

Data Index: 940741 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1019077 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2294. Min Act: -0.0001

Data Index: 6831 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1107945 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2275. Min Act: -0.0001

Data Index: 1181169 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2241. Min Act: -0.0001

Data Index: 868241 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2153. Min Act: -0.0001

Data Index: 62186 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1230396 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2147. Min Act: -0.0001

Data Index: 1213048 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.2581. Min Range: -0.2581

Max Act: 0.2126. Min Act: -0.0000

Data Index: 367368 (C4 (Web Text))

Max Activating Token Index: 16