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

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

Neuron 3198 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: 0.7440. Min Range: -0.7440

Max Act: 0.7076. Min Act: -0.0001

Data Index: 1382191 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.7133. Min Act: -0.0001

Data Index: 1647705 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.7440. Min Act: -0.0001

Data Index: 1405578 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.6257. Min Act: -0.0001

Data Index: 1554719 (Python Code)

Max Activating Token Index: 711

Text #4

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5893. Min Act: -0.0001

Data Index: 1469678 (Python Code)

Max Activating Token Index: 203

Text #5

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.6027. Min Act: -0.0001

Data Index: 1390919 (Python Code)

Max Activating Token Index: 126

Text #6

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.6567. Min Act: -0.0001

Data Index: 1602353 (Python Code)

Max Activating Token Index: 934

Text #7

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5607. Min Act: -0.0001

Data Index: 1645407 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1592262 (Python Code)

Max Activating Token Index: 295

Text #9

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5748. Min Act: -0.0001

Data Index: 1457381 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5595. Min Act: -0.0001

Data Index: 1558816 (Python Code)

Max Activating Token Index: 968

Text #11

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5382. Min Act: -0.0001

Data Index: 1447487 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5690. Min Act: -0.0001

Data Index: 1572774 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5835. Min Act: -0.0001

Data Index: 1609514 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5575. Min Act: -0.0001

Data Index: 1634291 (Python Code)

Max Activating Token Index: 79

Text #15

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5126. Min Act: -0.0001

Data Index: 1461898 (Python Code)

Max Activating Token Index: 151

Text #16

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5160. Min Act: -0.0001

Data Index: 1448076 (Python Code)

Max Activating Token Index: 116

Text #17

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5352. Min Act: -0.0001

Data Index: 1373636 (Python Code)

Max Activating Token Index: 496

Text #18

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5344. Min Act: -0.0001

Data Index: 1433248 (Python Code)

Max Activating Token Index: 515

Text #19

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5304. Min Act: -0.0001

Data Index: 1604685 (Python Code)

Max Activating Token Index: 463