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

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

Neuron 4005 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5619. Min Act: -0.0000

Data Index: 539230 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1287253 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1239656 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5165. Min Act: -0.0000

Data Index: 538665 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4832. Min Act: -0.0000

Data Index: 541109 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4920. Min Act: -0.0000

Data Index: 558860 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1290367 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1270030 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4720. Min Act: -0.0000

Data Index: 470966 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4999. Min Act: -0.0000

Data Index: 564057 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1266039 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4407. Min Act: -0.0000

Data Index: 279310 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4676. Min Act: -0.0000

Data Index: 562713 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4513. Min Act: -0.0000

Data Index: 224884 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4329. Min Act: -0.0000

Data Index: 186123 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3881. Min Act: -0.0000

Data Index: 208214 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3697. Min Act: -0.0000

Data Index: 338868 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1339596 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1082609 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1551776 (Python Code)

Max Activating Token Index: 300