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

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

Neuron 3824 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.6578. Min Act: -0.0000

Data Index: 388423 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.4975. Min Act: -0.0000

Data Index: 1562800 (Python Code)

Max Activating Token Index: 385

Text #2

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.4161. Min Act: -0.0000

Data Index: 1173068 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3011. Min Act: -0.0000

Data Index: 194252 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.1020. Min Act: -0.0000

Data Index: 928872 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.8773. Min Act: -0.0000

Data Index: 1442220 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.9253. Min Act: -0.0000

Data Index: 560346 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.8113. Min Act: -0.0000

Data Index: 613875 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.9185. Min Act: -0.0000

Data Index: 1365704 (Python Code)

Max Activating Token Index: 341

Text #9

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.3464. Min Act: -0.0000

Data Index: 665800 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.6153. Min Act: -0.0000

Data Index: 863373 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.5963. Min Act: -0.0000

Data Index: 849449 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.5812. Min Act: -0.0000

Data Index: 372559 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.4594. Min Act: -0.0000

Data Index: 1311774 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.6371. Min Act: -0.0000

Data Index: 1247750 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.6535. Min Act: -0.0000

Data Index: 1188570 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.7482. Min Act: -0.0000

Data Index: 570927 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.6947. Min Act: -0.0000

Data Index: 416066 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.7004. Min Act: -0.0000

Data Index: 167130 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 3.6578. Min Range: -3.6578

Max Act: 2.4401. Min Act: -0.0000

Data Index: 1285699 (C4 (Web Text))

Max Activating Token Index: 989