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

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

Neuron 1713 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3867. Min Act: -0.0000

Data Index: 810949 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3717. Min Act: -0.0000

Data Index: 985203 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3464. Min Act: -0.0000

Data Index: 71 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2914. Min Act: -0.0000

Data Index: 887940 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2955. Min Act: -0.0000

Data Index: 706325 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2907. Min Act: -0.0000

Data Index: 703432 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2569. Min Act: -0.0000

Data Index: 6586 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2429. Min Act: -0.0000

Data Index: 825660 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2503. Min Act: -0.0000

Data Index: 916410 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2450. Min Act: -0.0000

Data Index: 189102 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2502. Min Act: -0.0000

Data Index: 569482 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2338. Min Act: -0.0000

Data Index: 302583 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2422. Min Act: -0.0000

Data Index: 947960 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2425. Min Act: -0.0000

Data Index: 708134 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2338. Min Act: -0.0000

Data Index: 282003 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2346. Min Act: -0.0000

Data Index: 283448 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2267. Min Act: -0.0000

Data Index: 586716 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2312. Min Act: -0.0000

Data Index: 777314 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1343074 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2344. Min Act: -0.0000

Data Index: 67231 (C4 (Web Text))

Max Activating Token Index: 201