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

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

Neuron 1699 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.9553. Min Act: -0.0001

Data Index: 1517311 (Python Code)

Max Activating Token Index: 351

Text #1

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.4478. Min Act: -0.0001

Data Index: 1550949 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.4525. Min Act: -0.0001

Data Index: 1390869 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3938. Min Act: -0.0001

Data Index: 419598 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3957. Min Act: -0.0001

Data Index: 1563123 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3538. Min Act: -0.0001

Data Index: 1575970 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3789. Min Act: -0.0001

Data Index: 707387 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3022. Min Act: -0.0001

Data Index: 1250194 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3691. Min Act: -0.0001

Data Index: 1011871 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3673. Min Act: -0.0001

Data Index: 1041913 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3429. Min Act: -0.0001

Data Index: 1498243 (Python Code)

Max Activating Token Index: 668

Text #11

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.4177. Min Act: -0.0001

Data Index: 1606023 (Python Code)

Max Activating Token Index: 873

Text #12

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3152. Min Act: -0.0001

Data Index: 1573651 (Python Code)

Max Activating Token Index: 762

Text #13

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.2903. Min Act: -0.0001

Data Index: 1333955 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3134. Min Act: -0.0001

Data Index: 447361 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3140. Min Act: -0.0001

Data Index: 1506749 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.2705. Min Act: -0.0001

Data Index: 1455229 (Python Code)

Max Activating Token Index: 852

Text #17

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3021. Min Act: -0.0001

Data Index: 1575280 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.2833. Min Act: -0.0001

Data Index: 1496673 (Python Code)

Max Activating Token Index: 549

Text #19

Max Range: 1.9553. Min Range: -1.9553

Max Act: 1.3772. Min Act: -0.0001

Data Index: 1409728 (Python Code)

Max Activating Token Index: 402