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

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

Neuron 274 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: 1.9397. Min Range: -1.9397

Max Act: 1.9397. Min Act: -0.0000

Data Index: 1495925 (Python Code)

Max Activating Token Index: 674

Text #1

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1443275 (Python Code)

Max Activating Token Index: 114

Text #2

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.7292. Min Act: -0.0001

Data Index: 1492445 (Python Code)

Max Activating Token Index: 230

Text #3

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.6752. Min Act: -0.0000

Data Index: 1622903 (Python Code)

Max Activating Token Index: 786

Text #4

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.7555. Min Act: -0.0001

Data Index: 1333108 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.5302. Min Act: -0.0001

Data Index: 1530298 (Python Code)

Max Activating Token Index: 414

Text #6

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.5976. Min Act: -0.0000

Data Index: 1631847 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.5690. Min Act: -0.0000

Data Index: 1520842 (Python Code)

Max Activating Token Index: 385

Text #8

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1636950 (Python Code)

Max Activating Token Index: 263

Text #9

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1364296 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.5003. Min Act: -0.0000

Data Index: 1448009 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.4946. Min Act: -0.0000

Data Index: 1435053 (Python Code)

Max Activating Token Index: 895

Text #12

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.5933. Min Act: -0.0001

Data Index: 1457646 (Python Code)

Max Activating Token Index: 425

Text #13

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1313685 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.4290. Min Act: -0.0000

Data Index: 1557313 (Python Code)

Max Activating Token Index: 825

Text #15

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1538162 (Python Code)

Max Activating Token Index: 857

Text #16

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.5062. Min Act: -0.0001

Data Index: 827929 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.4096. Min Act: -0.0001

Data Index: 109954 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.3276. Min Act: -0.0001

Data Index: 1402775 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 1.9397. Min Range: -1.9397

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1456096 (Python Code)

Max Activating Token Index: 43