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

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

Neuron 1564 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.4020. Min Act: -0.0001

Data Index: 1174964 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.1828. Min Act: -0.0001

Data Index: 510321 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0830. Min Act: -0.0001

Data Index: 787350 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0514. Min Act: -0.0001

Data Index: 364321 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.9238. Min Act: -0.0001

Data Index: 901786 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0274. Min Act: -0.0001

Data Index: 1042332 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0065. Min Act: -0.0001

Data Index: 872120 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1269399 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.9282. Min Act: -0.0001

Data Index: 1103994 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.8692. Min Act: -0.0001

Data Index: 670995 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.9034. Min Act: -0.0001

Data Index: 321288 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.8155. Min Act: -0.0001

Data Index: 157941 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.8966. Min Act: -0.0001

Data Index: 1148239 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.8811. Min Act: -0.0001

Data Index: 255418 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.8219. Min Act: -0.0001

Data Index: 996271 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.8475. Min Act: -0.0001

Data Index: 699353 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.8289. Min Act: -0.0001

Data Index: 1211989 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.9097. Min Act: -0.0001

Data Index: 800311 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.7386. Min Act: -0.0001

Data Index: 977614 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.7755. Min Act: -0.0001

Data Index: 377488 (C4 (Web Text))

Max Activating Token Index: 448