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

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

Neuron 1226 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.3707. Min Act: -0.0001

Data Index: 1407323 (Python Code)

Max Activating Token Index: 547

Text #1

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.4077. Min Act: -0.0001

Data Index: 1527210 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.4946. Min Act: -0.0001

Data Index: 1441543 (Python Code)

Max Activating Token Index: 999

Text #3

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.3549. Min Act: -0.0001

Data Index: 1363518 (Python Code)

Max Activating Token Index: 585

Text #4

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.1227. Min Act: -0.0001

Data Index: 1643876 (Python Code)

Max Activating Token Index: 846

Text #5

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.0598. Min Act: -0.0001

Data Index: 1399312 (Python Code)

Max Activating Token Index: 732

Text #6

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.2303. Min Act: -0.0001

Data Index: 1441697 (Python Code)

Max Activating Token Index: 668

Text #7

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.2274. Min Act: -0.0001

Data Index: 1639985 (Python Code)

Max Activating Token Index: 751

Text #8

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.0103. Min Act: -0.0001

Data Index: 1429082 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.1517. Min Act: -0.0001

Data Index: 1549661 (Python Code)

Max Activating Token Index: 810

Text #10

Max Range: 5.4946. Min Range: -5.4946

Max Act: 4.9812. Min Act: -0.0001

Data Index: 1639114 (Python Code)

Max Activating Token Index: 923

Text #11

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.1048. Min Act: -0.0001

Data Index: 1581400 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 5.4946. Min Range: -5.4946

Max Act: 4.9129. Min Act: -0.0001

Data Index: 1507817 (Python Code)

Max Activating Token Index: 1009

Text #13

Max Range: 5.4946. Min Range: -5.4946

Max Act: 4.9072. Min Act: -0.0001

Data Index: 1476219 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 5.4946. Min Range: -5.4946

Max Act: 5.0343. Min Act: -0.0001

Data Index: 1414080 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 5.4946. Min Range: -5.4946

Max Act: 4.8420. Min Act: -0.0001

Data Index: 1510689 (Python Code)

Max Activating Token Index: 738

Text #16

Max Range: 5.4946. Min Range: -5.4946

Max Act: 4.9133. Min Act: -0.0001

Data Index: 1612372 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 5.4946. Min Range: -5.4946

Max Act: 4.9127. Min Act: -0.0001

Data Index: 1626624 (Python Code)

Max Activating Token Index: 627

Text #18

Max Range: 5.4946. Min Range: -5.4946

Max Act: 4.5333. Min Act: -0.0001

Data Index: 1429806 (Python Code)

Max Activating Token Index: 888

Text #19

Max Range: 5.4946. Min Range: -5.4946

Max Act: 4.5025. Min Act: -0.0001

Data Index: 1532996 (Python Code)

Max Activating Token Index: 453