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

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

Neuron 3897 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.8012. Min Act: -0.0000

Data Index: 595485 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.2979. Min Act: -0.0000

Data Index: 1542584 (Python Code)

Max Activating Token Index: 241

Text #2

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.0813. Min Act: -0.0000

Data Index: 1141072 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.9038. Min Act: -0.0000

Data Index: 1098258 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.0843. Min Act: -0.0000

Data Index: 389626 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.8597. Min Act: -0.0000

Data Index: 658264 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.8570. Min Act: -0.0000

Data Index: 803126 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.7147. Min Act: -0.0000

Data Index: 534436 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.5975. Min Act: -0.0000

Data Index: 848887 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.7745. Min Act: -0.0000

Data Index: 1517768 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.6726. Min Act: -0.0000

Data Index: 1149703 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.6658. Min Act: -0.0000

Data Index: 1536706 (Python Code)

Max Activating Token Index: 289

Text #12

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.6521. Min Act: -0.0000

Data Index: 699760 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.7324. Min Act: -0.0000

Data Index: 272537 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.7259. Min Act: -0.0000

Data Index: 63707 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.7203. Min Act: -0.0000

Data Index: 745495 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.8042. Min Act: -0.0000

Data Index: 262916 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.4252. Min Act: -0.0000

Data Index: 724119 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.5988. Min Act: -0.0000

Data Index: 890311 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.6986. Min Act: -0.0000

Data Index: 652434 (C4 (Web Text))

Max Activating Token Index: 674