Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 438 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4877. Min Act: -0.0000

Data Index: 492493 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4803. Min Act: -0.0001

Data Index: 553063 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4814. Min Act: -0.0001

Data Index: 1088999 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4207. Min Act: -0.0000

Data Index: 777861 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4764. Min Act: -0.0001

Data Index: 613277 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4490. Min Act: -0.0000

Data Index: 464220 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4397. Min Act: -0.0000

Data Index: 747010 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4739. Min Act: -0.0001

Data Index: 167793 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4126. Min Act: -0.0001

Data Index: 79928 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.3772. Min Act: -0.0000

Data Index: 887320 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4452. Min Act: -0.0001

Data Index: 965016 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.3613. Min Act: -0.0000

Data Index: 86646 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4228. Min Act: -0.0001

Data Index: 765386 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.3950. Min Act: -0.0001

Data Index: 1318485 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.3702. Min Act: -0.0000

Data Index: 852015 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1060293 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1016670 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4003. Min Act: -0.0000

Data Index: 401220 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1444057 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4043. Min Act: -0.0001

Data Index: 789241 (C4 (Web Text))

Max Activating Token Index: 313