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

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

Neuron 3855 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.8491. Min Act: -0.0002

Data Index: 689246 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.8231. Min Act: -0.0002

Data Index: 989691 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7726. Min Act: -0.0002

Data Index: 1084929 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7490. Min Act: -0.0002

Data Index: 97717 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7300. Min Act: -0.0002

Data Index: 818128 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7035. Min Act: -0.0002

Data Index: 712487 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7197. Min Act: -0.0002

Data Index: 246185 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6972. Min Act: -0.0002

Data Index: 224882 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7179. Min Act: -0.0002

Data Index: 1304324 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7215. Min Act: -0.0002

Data Index: 453808 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6990. Min Act: -0.0002

Data Index: 123607 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7144. Min Act: -0.0002

Data Index: 449342 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6948. Min Act: -0.0002

Data Index: 738784 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6709. Min Act: -0.0002

Data Index: 995726 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6278. Min Act: -0.0002

Data Index: 499643 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6682. Min Act: -0.0002

Data Index: 392249 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6423. Min Act: -0.0002

Data Index: 793731 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6357. Min Act: -0.0002

Data Index: 466052 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6153. Min Act: -0.0002

Data Index: 834211 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6340. Min Act: -0.0002

Data Index: 1233884 (C4 (Web Text))

Max Activating Token Index: 542