Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 219 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.5183. Min Range: -4.5183

Max Act: 4.5183. Min Act: -0.0000

Data Index: 1618255 (Python Code)

Max Activating Token Index: 189

Text #1

Max Range: 4.5183. Min Range: -4.5183

Max Act: 4.3464. Min Act: -0.0000

Data Index: 1569110 (Python Code)

Max Activating Token Index: 517

Text #2

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.9353. Min Act: -0.0000

Data Index: 1582709 (Python Code)

Max Activating Token Index: 328

Text #3

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.4151. Min Act: -0.0000

Data Index: 1644203 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.1824. Min Act: -0.0000

Data Index: 1361699 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.2161. Min Act: -0.0000

Data Index: 1651593 (Python Code)

Max Activating Token Index: 208

Text #6

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.1694. Min Act: -0.0000

Data Index: 1383719 (Python Code)

Max Activating Token Index: 860

Text #7

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.1288. Min Act: -0.0000

Data Index: 1540553 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.1268. Min Act: -0.0000

Data Index: 1546522 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.2456. Min Act: -0.0001

Data Index: 1565856 (Python Code)

Max Activating Token Index: 724

Text #10

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.0786. Min Act: -0.0000

Data Index: 1566270 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 4.5183. Min Range: -4.5183

Max Act: 2.9213. Min Act: -0.0001

Data Index: 1501801 (Python Code)

Max Activating Token Index: 514

Text #12

Max Range: 4.5183. Min Range: -4.5183

Max Act: 2.9143. Min Act: -0.0000

Data Index: 1615284 (Python Code)

Max Activating Token Index: 714

Text #13

Max Range: 4.5183. Min Range: -4.5183

Max Act: 2.7709. Min Act: -0.0000

Data Index: 1433277 (Python Code)

Max Activating Token Index: 809

Text #14

Max Range: 4.5183. Min Range: -4.5183

Max Act: 2.8941. Min Act: -0.0001

Data Index: 1380041 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.0184. Min Act: -0.0000

Data Index: 1651106 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 4.5183. Min Range: -4.5183

Max Act: 3.0184. Min Act: -0.0000

Data Index: 1365709 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 4.5183. Min Range: -4.5183

Max Act: 2.9447. Min Act: -0.0001

Data Index: 1650279 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 4.5183. Min Range: -4.5183

Max Act: 2.9435. Min Act: -0.0000

Data Index: 1420047 (Python Code)

Max Activating Token Index: 1008

Text #19

Max Range: 4.5183. Min Range: -4.5183

Max Act: 2.9220. Min Act: -0.0001

Data Index: 1450548 (Python Code)

Max Activating Token Index: 616