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

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

Neuron 6076 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.8021. Min Act: -0.0000

Data Index: 566859 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.7390. Min Act: -0.0000

Data Index: 1219870 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.7005. Min Act: -0.0000

Data Index: 234963 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.6558. Min Act: -0.0000

Data Index: 217186 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1011903 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.4585. Min Act: -0.0000

Data Index: 391358 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.5618. Min Act: -0.0000

Data Index: 332581 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.4714. Min Act: -0.0000

Data Index: 639651 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.4602. Min Act: -0.0000

Data Index: 1127559 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1025931 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1406481 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.2357. Min Act: -0.0000

Data Index: 63954 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.3824. Min Act: -0.0000

Data Index: 851603 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1498189 (Python Code)

Max Activating Token Index: 311

Text #14

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.3801. Min Act: -0.0000

Data Index: 194365 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.2617. Min Act: -0.0000

Data Index: 867165 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1002981 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.3414. Min Act: -0.0000

Data Index: 689413 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.2389. Min Act: -0.0000

Data Index: 534619 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.8021. Min Range: -1.8021

Max Act: 1.1641. Min Act: -0.0000

Data Index: 22153 (C4 (Web Text))

Max Activating Token Index: 882