Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4115 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1849. Min Range: -2.1849

Max Act: 2.1612. Min Act: -0.0000

Data Index: 173629 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 2.1849. Min Range: -2.1849

Max Act: 2.1849. Min Act: -0.0000

Data Index: 1107353 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 2.1849. Min Range: -2.1849

Max Act: 2.0189. Min Act: -0.0000

Data Index: 544613 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.9163. Min Act: -0.0000

Data Index: 1287396 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.9442. Min Act: -0.0000

Data Index: 96207 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.8751. Min Act: -0.0000

Data Index: 1082417 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.8701. Min Act: -0.0000

Data Index: 590734 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.7798. Min Act: -0.0000

Data Index: 63192 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.8555. Min Act: -0.0000

Data Index: 219013 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.8681. Min Act: -0.0000

Data Index: 1310953 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.8438. Min Act: -0.0000

Data Index: 1411255 (Python Code)

Max Activating Token Index: 729

Text #11

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.9407. Min Act: -0.0000

Data Index: 1302265 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.7911. Min Act: -0.0000

Data Index: 248621 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.7464. Min Act: -0.0000

Data Index: 1049788 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.8005. Min Act: -0.0001

Data Index: 835247 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.8076. Min Act: -0.0000

Data Index: 350257 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.7804. Min Act: -0.0000

Data Index: 27086 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.6819. Min Act: -0.0000

Data Index: 465496 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.8472. Min Act: -0.0000

Data Index: 954702 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 2.1849. Min Range: -2.1849

Max Act: 1.7680. Min Act: -0.0000

Data Index: 272563 (C4 (Web Text))

Max Activating Token Index: 76