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

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

Neuron 6031 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: 1.5633. Min Range: -1.5633

Max Act: 1.5633. Min Act: -0.0000

Data Index: 1299626 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 1.5633. Min Range: -1.5633

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1467219 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 1.5633. Min Range: -1.5633

Max Act: 1.1481. Min Act: 0.0000

Data Index: 685680 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 1.5633. Min Range: -1.5633

Max Act: 1.0134. Min Act: -0.0000

Data Index: 4204 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 1.5633. Min Range: -1.5633

Max Act: 1.0450. Min Act: 0.0000

Data Index: 152273 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 1.5633. Min Range: -1.5633

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1256794 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.9442. Min Act: -0.0000

Data Index: 147865 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.9525. Min Act: -0.0000

Data Index: 439324 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.9455. Min Act: -0.0000

Data Index: 614063 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.9099. Min Act: -0.0000

Data Index: 681024 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.9283. Min Act: 0.0000

Data Index: 665199 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.8697. Min Act: -0.0000

Data Index: 383133 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.5633. Min Range: -1.5633

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1425588 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.9532. Min Act: 0.0000

Data Index: 1297432 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.8475. Min Act: -0.0000

Data Index: 379223 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.8444. Min Act: -0.0000

Data Index: 253030 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.8221. Min Act: -0.0000

Data Index: 317070 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.8581. Min Act: -0.0000

Data Index: 797055 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1477890 (Python Code)

Max Activating Token Index: 924

Text #19

Max Range: 1.5633. Min Range: -1.5633

Max Act: 0.8554. Min Act: -0.0000

Data Index: 41522 (C4 (Web Text))

Max Activating Token Index: 495