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

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

Neuron 1985 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2446. Min Range: -4.2446

Max Act: 4.2446. Min Act: -0.0001

Data Index: 1638985 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.9869. Min Act: -0.0001

Data Index: 1313139 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.4614. Min Act: -0.0001

Data Index: 1258952 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.5074. Min Act: -0.0001

Data Index: 649833 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.3047. Min Act: -0.0001

Data Index: 1290470 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.2442. Min Act: -0.0001

Data Index: 1183641 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.3441. Min Act: -0.0001

Data Index: 1157700 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.1969. Min Act: -0.0001

Data Index: 163332 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.1668. Min Act: -0.0001

Data Index: 1181277 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 4.2446. Min Range: -4.2446

Max Act: 2.9939. Min Act: -0.0001

Data Index: 343045 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 4.2446. Min Range: -4.2446

Max Act: 2.8520. Min Act: -0.0001

Data Index: 475479 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.3868. Min Act: -0.0001

Data Index: 767501 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.0792. Min Act: -0.0001

Data Index: 797489 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 4.2446. Min Range: -4.2446

Max Act: 2.8627. Min Act: -0.0001

Data Index: 396246 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 4.2446. Min Range: -4.2446

Max Act: 2.8703. Min Act: -0.0001

Data Index: 1073027 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 4.2446. Min Range: -4.2446

Max Act: 2.9476. Min Act: -0.0001

Data Index: 211352 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 4.2446. Min Range: -4.2446

Max Act: 3.0204. Min Act: -0.0001

Data Index: 260434 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 4.2446. Min Range: -4.2446

Max Act: 2.9313. Min Act: -0.0001

Data Index: 1274753 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 4.2446. Min Range: -4.2446

Max Act: 2.8767. Min Act: -0.0001

Data Index: 627289 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 4.2446. Min Range: -4.2446

Max Act: 2.6980. Min Act: -0.0001

Data Index: 283017 (C4 (Web Text))

Max Activating Token Index: 279