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

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

Neuron 4972 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8903. Min Act: -0.0000

Data Index: 888962 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7366. Min Act: -0.0000

Data Index: 1100272 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.8635. Min Act: -0.0000

Data Index: 874329 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.9163. Min Act: -0.0000

Data Index: 514512 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.9805. Min Act: -0.0000

Data Index: 407571 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1256062 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.9000. Min Act: -0.0000

Data Index: 642157 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.8940. Min Act: -0.0000

Data Index: 201730 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.8388. Min Act: -0.0000

Data Index: 222756 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.8551. Min Act: -0.0000

Data Index: 834292 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.8387. Min Act: -0.0000

Data Index: 687166 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.8452. Min Act: -0.0000

Data Index: 719369 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1188448 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.8014. Min Act: -0.0000

Data Index: 559623 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.7819. Min Act: -0.0000

Data Index: 624992 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.7528. Min Act: -0.0000

Data Index: 799388 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.8328. Min Act: -0.0000

Data Index: 176680 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.7582. Min Act: -0.0000

Data Index: 720245 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1251242 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 1.8903. Min Range: -1.8903

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1117369 (C4 (Web Text))

Max Activating Token Index: 459