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

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

Neuron 886 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1488669 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.6676. Min Act: -0.0000

Data Index: 629808 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.5216. Min Act: -0.0000

Data Index: 374928 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4947. Min Act: -0.0000

Data Index: 806678 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1290709 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4665. Min Act: -0.0000

Data Index: 404457 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1602618 (Python Code)

Max Activating Token Index: 732

Text #7

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4427. Min Act: -0.0000

Data Index: 958558 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4333. Min Act: -0.0000

Data Index: 520945 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4143. Min Act: -0.0001

Data Index: 1565978 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1556526 (Python Code)

Max Activating Token Index: 1002

Text #11

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1246662 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4027. Min Act: -0.0000

Data Index: 538981 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1412632 (Python Code)

Max Activating Token Index: 922

Text #14

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1457103 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1112624 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.3988. Min Act: -0.0000

Data Index: 645844 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.3977. Min Act: -0.0000

Data Index: 336195 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.3920. Min Act: -0.0000

Data Index: 237186 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1626452 (Python Code)

Max Activating Token Index: 273