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

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

Neuron 910 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.8887. Min Act: -0.0000

Data Index: 577903 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1642389 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1434101 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7118. Min Act: -0.0000

Data Index: 268045 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7430. Min Act: -0.0000

Data Index: 675210 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1610374 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6723. Min Act: -0.0000

Data Index: 954238 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1317117 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1474336 (Python Code)

Max Activating Token Index: 259

Text #9

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6385. Min Act: -0.0000

Data Index: 574962 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6143. Min Act: -0.0000

Data Index: 921920 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6318. Min Act: 0.0000

Data Index: 511593 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1435020 (Python Code)

Max Activating Token Index: 663

Text #13

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1168591 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6224. Min Act: -0.0000

Data Index: 485174 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1479980 (Python Code)

Max Activating Token Index: 261

Text #16

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.5711. Min Act: -0.0000

Data Index: 302727 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.5757. Min Act: -0.0000

Data Index: 170910 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6014. Min Act: 0.0000

Data Index: 1170772 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.5710. Min Act: -0.0000

Data Index: 819554 (C4 (Web Text))

Max Activating Token Index: 70