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

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

Neuron 4626 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1506362 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1319325 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1463500 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6557. Min Act: -0.0000

Data Index: 979423 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6279. Min Act: -0.0000

Data Index: 597175 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6273. Min Act: 0.0000

Data Index: 1281046 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6144. Min Act: -0.0000

Data Index: 412013 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1407599 (Python Code)

Max Activating Token Index: 423

Text #8

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1653700 (Python Code)

Max Activating Token Index: 661

Text #9

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1522264 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1436260 (Python Code)

Max Activating Token Index: 952

Text #11

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1618367 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5145. Min Act: -0.0000

Data Index: 860436 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1641191 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5144. Min Act: -0.0000

Data Index: 319251 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1554266 (Python Code)

Max Activating Token Index: 600

Text #16

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.4749. Min Act: -0.0000

Data Index: 283769 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.4492. Min Act: -0.0000

Data Index: 542948 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.4656. Min Act: 0.0000

Data Index: 1150456 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.4661. Min Act: -0.0000

Data Index: 268051 (C4 (Web Text))

Max Activating Token Index: 21