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

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

Neuron 2749 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6685. Min Range: -2.6685

Max Act: 2.6685. Min Act: -0.0000

Data Index: 1434080 (Python Code)

Max Activating Token Index: 906

Text #1

Max Range: 2.6685. Min Range: -2.6685

Max Act: 2.4578. Min Act: -0.0000

Data Index: 174474 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.9150. Min Act: -0.0000

Data Index: 1591304 (Python Code)

Max Activating Token Index: 179

Text #3

Max Range: 2.6685. Min Range: -2.6685

Max Act: 2.1381. Min Act: -0.0000

Data Index: 219637 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 2.6685. Min Range: -2.6685

Max Act: 2.1049. Min Act: -0.0000

Data Index: 1536399 (Python Code)

Max Activating Token Index: 843

Text #5

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.8743. Min Act: -0.0000

Data Index: 1553209 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.8538. Min Act: -0.0000

Data Index: 1088336 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.5356. Min Act: -0.0000

Data Index: 1413613 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.7317. Min Act: -0.0000

Data Index: 1406706 (Python Code)

Max Activating Token Index: 550

Text #9

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.5806. Min Act: -0.0000

Data Index: 1133250 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.5915. Min Act: -0.0000

Data Index: 1088621 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.8120. Min Act: -0.0000

Data Index: 1528103 (Python Code)

Max Activating Token Index: 687

Text #12

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.7211. Min Act: -0.0000

Data Index: 1435826 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.5913. Min Act: -0.0000

Data Index: 821710 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.6942. Min Act: -0.0000

Data Index: 1042395 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1515584 (Python Code)

Max Activating Token Index: 209

Text #16

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.7904. Min Act: -0.0000

Data Index: 1362721 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.6327. Min Act: -0.0000

Data Index: 537410 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.4664. Min Act: -0.0000

Data Index: 1451659 (Python Code)

Max Activating Token Index: 663

Text #19

Max Range: 2.6685. Min Range: -2.6685

Max Act: 1.5940. Min Act: -0.0000

Data Index: 474665 (C4 (Web Text))

Max Activating Token Index: 898