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

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

Neuron 4389 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3861. Min Range: -4.3861

Max Act: 4.1462. Min Act: -0.0001

Data Index: 834889 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 4.3861. Min Range: -4.3861

Max Act: 4.3861. Min Act: -0.0001

Data Index: 483933 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.5619. Min Act: -0.0001

Data Index: 794366 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.6699. Min Act: -0.0001

Data Index: 999024 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.4933. Min Act: -0.0001

Data Index: 194107 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.5962. Min Act: -0.0001

Data Index: 1259741 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.5692. Min Act: -0.0001

Data Index: 1131454 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.8341. Min Act: -0.0001

Data Index: 388282 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.3849. Min Act: -0.0001

Data Index: 537299 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.5222. Min Act: -0.0001

Data Index: 776614 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.4934. Min Act: -0.0001

Data Index: 1140283 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.4297. Min Act: -0.0001

Data Index: 1239422 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.4673. Min Act: -0.0001

Data Index: 398032 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.4474. Min Act: -0.0001

Data Index: 691203 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.2716. Min Act: -0.0001

Data Index: 491832 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.4033. Min Act: -0.0001

Data Index: 176483 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.5302. Min Act: -0.0000

Data Index: 937109 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.5313. Min Act: -0.0001

Data Index: 703580 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.3815. Min Act: -0.0001

Data Index: 995909 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 4.3861. Min Range: -4.3861

Max Act: 3.3548. Min Act: -0.0001

Data Index: 282602 (C4 (Web Text))

Max Activating Token Index: 421