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

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

Neuron 3121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8981. Min Act: -0.0001

Data Index: 832848 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8582. Min Act: -0.0001

Data Index: 1160197 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7369. Min Act: -0.0000

Data Index: 173064 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7277. Min Act: -0.0000

Data Index: 483399 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7172. Min Act: -0.0000

Data Index: 598382 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7678. Min Act: -0.0001

Data Index: 1137642 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6885. Min Act: -0.0001

Data Index: 932562 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6445. Min Act: -0.0000

Data Index: 540936 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6755. Min Act: -0.0001

Data Index: 1199427 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.5746. Min Act: -0.0000

Data Index: 862898 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6634. Min Act: -0.0000

Data Index: 736899 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6338. Min Act: -0.0001

Data Index: 260830 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6531. Min Act: -0.0001

Data Index: 117349 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.5551. Min Act: -0.0001

Data Index: 244900 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.5487. Min Act: -0.0000

Data Index: 966695 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.5865. Min Act: -0.0000

Data Index: 258018 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6251. Min Act: -0.0001

Data Index: 536858 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6022. Min Act: -0.0000

Data Index: 865301 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.5778. Min Act: -0.0001

Data Index: 215205 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.5641. Min Act: -0.0001

Data Index: 221514 (C4 (Web Text))

Max Activating Token Index: 433