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

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

Neuron 4598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1135450 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1162227 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1125953 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3072. Min Act: -0.0000

Data Index: 601198 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3482. Min Act: -0.0000

Data Index: 453840 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3145. Min Act: -0.0000

Data Index: 300475 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3133. Min Act: -0.0000

Data Index: 695988 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3207. Min Act: -0.0000

Data Index: 718897 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2914. Min Act: -0.0000

Data Index: 255927 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1090048 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2316. Min Act: -0.0000

Data Index: 636041 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2355. Min Act: -0.0000

Data Index: 239368 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2484. Min Act: -0.0000

Data Index: 775620 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1052963 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1518699 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1433815 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2382. Min Act: -0.0000

Data Index: 74370 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2363. Min Act: -0.0000

Data Index: 578864 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1132578 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.2265. Min Act: -0.0000

Data Index: 661860 (C4 (Web Text))

Max Activating Token Index: 160