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

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

Neuron 2158 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: 8.6433. Min Range: -8.6433

Max Act: 8.6433. Min Act: -0.0000

Data Index: 1648172 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 8.6433. Min Range: -8.6433

Max Act: 8.3787. Min Act: -0.0000

Data Index: 1530623 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 8.6433. Min Range: -8.6433

Max Act: 8.0816. Min Act: -0.0001

Data Index: 1578959 (Python Code)

Max Activating Token Index: 230

Text #3

Max Range: 8.6433. Min Range: -8.6433

Max Act: 8.2549. Min Act: -0.0000

Data Index: 1412261 (Python Code)

Max Activating Token Index: 109

Text #4

Max Range: 8.6433. Min Range: -8.6433

Max Act: 8.0307. Min Act: -0.0000

Data Index: 1473699 (Python Code)

Max Activating Token Index: 136

Text #5

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.9670. Min Act: -0.0001

Data Index: 1589828 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.6375. Min Act: -0.0000

Data Index: 1544206 (Python Code)

Max Activating Token Index: 78

Text #7

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.8115. Min Act: -0.0000

Data Index: 1428057 (Python Code)

Max Activating Token Index: 286

Text #8

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.6952. Min Act: -0.0000

Data Index: 1425623 (Python Code)

Max Activating Token Index: 129

Text #9

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.6777. Min Act: -0.0000

Data Index: 1546253 (Python Code)

Max Activating Token Index: 541

Text #10

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.8182. Min Act: -0.0000

Data Index: 1544159 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.6094. Min Act: -0.0000

Data Index: 1531933 (Python Code)

Max Activating Token Index: 674

Text #12

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.7250. Min Act: -0.0001

Data Index: 1649691 (Python Code)

Max Activating Token Index: 137

Text #13

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.1376. Min Act: -0.0000

Data Index: 1458905 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.4542. Min Act: -0.0001

Data Index: 1490633 (Python Code)

Max Activating Token Index: 811

Text #15

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.5332. Min Act: -0.0000

Data Index: 1404182 (Python Code)

Max Activating Token Index: 622

Text #16

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.7039. Min Act: -0.0000

Data Index: 1546987 (Python Code)

Max Activating Token Index: 682

Text #17

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.1441. Min Act: -0.0000

Data Index: 1420995 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 8.6433. Min Range: -8.6433

Max Act: 7.3109. Min Act: -0.0000

Data Index: 1489787 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 8.6433. Min Range: -8.6433

Max Act: 6.9398. Min Act: -0.0001

Data Index: 1509068 (Python Code)

Max Activating Token Index: 26