Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1153 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1067227 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1082299 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6340. Min Act: -0.0000

Data Index: 330789 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1122476 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5863. Min Act: -0.0000

Data Index: 783589 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5784. Min Act: -0.0000

Data Index: 497919 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5815. Min Act: -0.0000

Data Index: 87254 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5873. Min Act: -0.0000

Data Index: 439627 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5330. Min Act: 0.0000

Data Index: 1037935 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5771. Min Act: -0.0000

Data Index: 864386 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5394. Min Act: -0.0000

Data Index: 733994 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5365. Min Act: -0.0000

Data Index: 520608 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1654482 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5292. Min Act: -0.0000

Data Index: 385028 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5301. Min Act: -0.0000

Data Index: 67990 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5202. Min Act: -0.0000

Data Index: 454603 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5233. Min Act: -0.0000

Data Index: 575229 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.4843. Min Act: -0.0000

Data Index: 327919 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5002. Min Act: 0.0000

Data Index: 58324 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1571505 (Python Code)

Max Activating Token Index: 983