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

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

Neuron 4234 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1377031 (Python Code)

Max Activating Token Index: 646

Text #1

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1572605 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0775. Min Act: -0.0001

Data Index: 748401 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1573185 (Python Code)

Max Activating Token Index: 961

Text #4

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1057331 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0735. Min Act: -0.0001

Data Index: 934857 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1593202 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1475755 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0648. Min Act: -0.0001

Data Index: 293115 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1607671 (Python Code)

Max Activating Token Index: 1009

Text #10

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1311681 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1091910 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0697. Min Act: -0.0001

Data Index: 173235 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1493481 (Python Code)

Max Activating Token Index: 257

Text #14

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1432643 (Python Code)

Max Activating Token Index: 663

Text #15

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1546224 (Python Code)

Max Activating Token Index: 471

Text #16

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1531874 (Python Code)

Max Activating Token Index: 556

Text #17

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1511560 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0576. Min Act: -0.0001

Data Index: 506961 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0567. Min Act: -0.0001

Data Index: 588323 (C4 (Web Text))

Max Activating Token Index: 860