Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 245 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3488. Min Act: -0.0001

Data Index: 741179 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2756. Min Act: -0.0001

Data Index: 954691 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2682. Min Act: -0.0001

Data Index: 1017444 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2688. Min Act: -0.0001

Data Index: 227236 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2443. Min Act: -0.0001

Data Index: 473221 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2905. Min Act: -0.0001

Data Index: 836896 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2610. Min Act: -0.0001

Data Index: 1229345 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2785. Min Act: -0.0001

Data Index: 544615 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1132873 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2458. Min Act: -0.0001

Data Index: 695998 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2244. Min Act: -0.0001

Data Index: 380720 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2888. Min Act: -0.0001

Data Index: 341346 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2294. Min Act: -0.0001

Data Index: 1223662 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2330. Min Act: -0.0001

Data Index: 1181187 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2336. Min Act: -0.0001

Data Index: 175730 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2152. Min Act: -0.0001

Data Index: 450201 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2068. Min Act: -0.0001

Data Index: 1029125 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2364. Min Act: -0.0001

Data Index: 1269490 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2224. Min Act: -0.0001

Data Index: 877862 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2195. Min Act: -0.0001

Data Index: 684803 (C4 (Web Text))

Max Activating Token Index: 684