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

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

Neuron 1594 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: 0.4466. Min Range: -0.4466

Max Act: 0.4466. Min Act: -0.0001

Data Index: 1057916 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.4271. Min Act: -0.0001

Data Index: 330880 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3763. Min Act: -0.0001

Data Index: 503784 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1001554 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3712. Min Act: -0.0001

Data Index: 73871 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3569. Min Act: -0.0001

Data Index: 806128 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1077216 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3382. Min Act: 0.0000

Data Index: 795623 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3243. Min Act: -0.0001

Data Index: 1216691 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3266. Min Act: -0.0001

Data Index: 1075710 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3351. Min Act: -0.0001

Data Index: 563897 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3255. Min Act: 0.0002

Data Index: 1046464 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3325. Min Act: -0.0001

Data Index: 877502 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3277. Min Act: -0.0001

Data Index: 133579 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3239. Min Act: -0.0001

Data Index: 179847 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3243. Min Act: -0.0001

Data Index: 1283499 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1137517 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3209. Min Act: -0.0001

Data Index: 902670 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2976. Min Act: -0.0001

Data Index: 788550 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2663. Min Act: -0.0001

Data Index: 838898 (C4 (Web Text))

Max Activating Token Index: 60