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

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

Neuron 3216 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: 1.4102. Min Range: -1.4102

Max Act: 1.4102. Min Act: 0.0000

Data Index: 1007949 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1018120 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.2960. Min Act: -0.0000

Data Index: 421749 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.2314. Min Act: -0.0000

Data Index: 495265 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.2424. Min Act: -0.0000

Data Index: 226702 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.2270. Min Act: -0.0000

Data Index: 903980 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.2977. Min Act: -0.0000

Data Index: 809887 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1179276 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.2420. Min Act: -0.0000

Data Index: 638805 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1534. Min Act: -0.0000

Data Index: 768701 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1376. Min Act: 0.0000

Data Index: 181805 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1236894 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0986. Min Act: -0.0000

Data Index: 340243 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1447. Min Act: -0.0000

Data Index: 36867 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1277056 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0568. Min Act: -0.0000

Data Index: 673835 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1063. Min Act: -0.0000

Data Index: 156398 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0617. Min Act: -0.0000

Data Index: 431956 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0415. Min Act: -0.0000

Data Index: 497732 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.9319. Min Act: -0.0000

Data Index: 26055 (C4 (Web Text))

Max Activating Token Index: 997