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

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

Neuron 1951 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.6099. Min Act: -0.0001

Data Index: 80934 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.3419. Min Act: -0.0001

Data Index: 961803 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.3580. Min Act: -0.0001

Data Index: 1307053 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.1448. Min Act: -0.0001

Data Index: 1071413 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.2826. Min Act: -0.0001

Data Index: 1084793 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.1404. Min Act: -0.0001

Data Index: 169184 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.1881. Min Act: -0.0001

Data Index: 327664 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.3250. Min Act: -0.0001

Data Index: 1002171 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.2262. Min Act: -0.0001

Data Index: 851223 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.2938. Min Act: -0.0001

Data Index: 61004 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.3364. Min Act: -0.0001

Data Index: 238344 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.3028. Min Act: -0.0001

Data Index: 723249 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.1472. Min Act: -0.0001

Data Index: 1328585 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.2493. Min Act: -0.0001

Data Index: 964905 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.1667. Min Act: -0.0001

Data Index: 1008412 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.1789. Min Act: -0.0001

Data Index: 1211323 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.2459. Min Act: -0.0001

Data Index: 264894 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.3147. Min Act: -0.0001

Data Index: 1346824 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.1142. Min Act: -0.0001

Data Index: 118681 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.6099. Min Range: -1.6099

Max Act: 1.2191. Min Act: -0.0001

Data Index: 1006698 (C4 (Web Text))

Max Activating Token Index: 163