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

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

Neuron 2605 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2538. Min Range: -1.2538

Max Act: 1.2538. Min Act: -0.0001

Data Index: 1450710 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 1.2538. Min Range: -1.2538

Max Act: 1.0812. Min Act: -0.0000

Data Index: 827107 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.2538. Min Range: -1.2538

Max Act: 1.0543. Min Act: -0.0001

Data Index: 1097514 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9685. Min Act: -0.0000

Data Index: 966238 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 1.2538. Min Range: -1.2538

Max Act: 1.0173. Min Act: -0.0001

Data Index: 466882 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.2538. Min Range: -1.2538

Max Act: 1.0103. Min Act: -0.0001

Data Index: 780874 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9687. Min Act: -0.0000

Data Index: 31702 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9986. Min Act: -0.0001

Data Index: 1444874 (Python Code)

Max Activating Token Index: 587

Text #8

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9571. Min Act: -0.0000

Data Index: 913648 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9897. Min Act: -0.0001

Data Index: 505618 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9571. Min Act: -0.0001

Data Index: 379164 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9386. Min Act: -0.0001

Data Index: 1276001 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9379. Min Act: -0.0001

Data Index: 986887 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9300. Min Act: -0.0000

Data Index: 894509 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.8995. Min Act: -0.0001

Data Index: 238841 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9140. Min Act: -0.0001

Data Index: 1484811 (Python Code)

Max Activating Token Index: 898

Text #16

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.8905. Min Act: -0.0001

Data Index: 1445765 (Python Code)

Max Activating Token Index: 786

Text #17

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9219. Min Act: -0.0001

Data Index: 860412 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9478. Min Act: -0.0001

Data Index: 1514756 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 1.2538. Min Range: -1.2538

Max Act: 0.9214. Min Act: -0.0000

Data Index: 395596 (C4 (Web Text))

Max Activating Token Index: 888