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

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

Neuron 3914 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: 0.8251. Min Range: -0.8251

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1479317 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1648280 (Python Code)

Max Activating Token Index: 516

Text #2

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1378468 (Python Code)

Max Activating Token Index: 80

Text #3

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1529726 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1594699 (Python Code)

Max Activating Token Index: 398

Text #5

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1650122 (Python Code)

Max Activating Token Index: 892

Text #6

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6347. Min Act: -0.0001

Data Index: 1393961 (Python Code)

Max Activating Token Index: 921

Text #7

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1531914 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1569161 (Python Code)

Max Activating Token Index: 277

Text #9

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1586324 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1417007 (Python Code)

Max Activating Token Index: 490

Text #11

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1440613 (Python Code)

Max Activating Token Index: 720

Text #12

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1655683 (Python Code)

Max Activating Token Index: 367

Text #13

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1607684 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1637880 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1503276 (Python Code)

Max Activating Token Index: 943

Text #16

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1489089 (Python Code)

Max Activating Token Index: 452

Text #17

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1657027 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1523611 (Python Code)

Max Activating Token Index: 802

Text #19

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1584681 (Python Code)

Max Activating Token Index: 195