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

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

Neuron 557 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.7283. Min Act: -0.0002

Data Index: 798885 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6979. Min Act: -0.0002

Data Index: 583864 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.7016. Min Act: -0.0002

Data Index: 733446 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.7089. Min Act: -0.0002

Data Index: 50697 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6946. Min Act: -0.0002

Data Index: 553680 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6747. Min Act: -0.0002

Data Index: 1043191 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6592. Min Act: -0.0002

Data Index: 10872 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6535. Min Act: -0.0002

Data Index: 808400 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6478. Min Act: -0.0002

Data Index: 912017 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6470. Min Act: -0.0002

Data Index: 607992 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6436. Min Act: -0.0002

Data Index: 17249 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6413. Min Act: -0.0002

Data Index: 507041 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6294. Min Act: -0.0002

Data Index: 901240 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6313. Min Act: -0.0002

Data Index: 705598 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6157. Min Act: -0.0002

Data Index: 657669 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6230. Min Act: -0.0002

Data Index: 192289 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6307. Min Act: -0.0002

Data Index: 1106083 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6147. Min Act: -0.0002

Data Index: 806956 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6224. Min Act: -0.0002

Data Index: 761609 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6267. Min Act: -0.0002

Data Index: 1194698 (C4 (Web Text))

Max Activating Token Index: 120