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

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

Neuron 3313 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.6197. Min Act: -0.0000

Data Index: 910829 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1312042 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.6521. Min Act: -0.0000

Data Index: 831729 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1431262 (Python Code)

Max Activating Token Index: 267

Text #4

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1228231 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1629759 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1380283 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1514440 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1204137 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1635900 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1476813 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1560605 (Python Code)

Max Activating Token Index: 683

Text #12

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1441325 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1655767 (Python Code)

Max Activating Token Index: 728

Text #14

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1561136 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1510522 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1421548 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1207631 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4614. Min Act: -0.0000

Data Index: 11394 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1138084 (C4 (Web Text))

Max Activating Token Index: 812