Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4649 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.7084. Min Act: -0.0001

Data Index: 1440275 (Python Code)

Max Activating Token Index: 915

Text #1

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.2485. Min Act: -0.0001

Data Index: 866079 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.3832. Min Act: -0.0001

Data Index: 895197 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.2254. Min Act: -0.0001

Data Index: 953057 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.0661. Min Act: -0.0001

Data Index: 40796 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.1396. Min Act: -0.0001

Data Index: 60015 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.0239. Min Act: -0.0001

Data Index: 1165270 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.0217. Min Act: -0.0001

Data Index: 705189 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 1.7084. Min Range: -1.7084

Max Act: 0.9768. Min Act: -0.0001

Data Index: 1157091 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.0436. Min Act: -0.0001

Data Index: 1334249 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.0069. Min Act: -0.0001

Data Index: 36670 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1344378 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.7084. Min Range: -1.7084

Max Act: 0.9172. Min Act: -0.0001

Data Index: 207574 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.0894. Min Act: -0.0001

Data Index: 347501 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.7084. Min Range: -1.7084

Max Act: 0.9435. Min Act: -0.0001

Data Index: 728979 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.0030. Min Act: -0.0001

Data Index: 830164 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 1.7084. Min Range: -1.7084

Max Act: 0.9731. Min Act: -0.0001

Data Index: 898277 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.7084. Min Range: -1.7084

Max Act: 0.9161. Min Act: -0.0001

Data Index: 1306335 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.0238. Min Act: -0.0001

Data Index: 1353551 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 1.7084. Min Range: -1.7084

Max Act: 0.9495. Min Act: -0.0001

Data Index: 228510 (C4 (Web Text))

Max Activating Token Index: 421