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

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

Neuron 2059 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.8977. Min Act: -0.0001

Data Index: 1576932 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.8626. Min Act: -0.0001

Data Index: 142268 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.9568. Min Act: -0.0002

Data Index: 1257355 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.8057. Min Act: -0.0001

Data Index: 1368085 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.7507. Min Act: -0.0001

Data Index: 1562041 (Python Code)

Max Activating Token Index: 434

Text #5

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.7713. Min Act: -0.0002

Data Index: 76827 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.8713. Min Act: -0.0001

Data Index: 581646 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.7482. Min Act: -0.0001

Data Index: 1374216 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.6612. Min Act: -0.0001

Data Index: 1068822 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.6990. Min Act: -0.0002

Data Index: 1026997 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1598447 (Python Code)

Max Activating Token Index: 1021

Text #11

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.6807. Min Act: -0.0001

Data Index: 1565075 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.6485. Min Act: -0.0001

Data Index: 149149 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.6587. Min Act: -0.0001

Data Index: 1480924 (Python Code)

Max Activating Token Index: 465

Text #14

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.5921. Min Act: -0.0001

Data Index: 1473323 (Python Code)

Max Activating Token Index: 433

Text #15

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.5627. Min Act: -0.0001

Data Index: 1518389 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.6996. Min Act: -0.0001

Data Index: 1538167 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.6425. Min Act: -0.0001

Data Index: 1470611 (Python Code)

Max Activating Token Index: 381

Text #18

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.6537. Min Act: -0.0002

Data Index: 54705 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.9568. Min Range: -0.9568

Max Act: 0.7486. Min Act: -0.0002

Data Index: 722001 (C4 (Web Text))

Max Activating Token Index: 608