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

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

Neuron 3959 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7809. Min Act: -0.0001

Data Index: 335664 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7340. Min Act: -0.0001

Data Index: 792419 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7520. Min Act: -0.0001

Data Index: 244994 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7165. Min Act: -0.0001

Data Index: 702609 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6514. Min Act: -0.0001

Data Index: 218569 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7038. Min Act: -0.0001

Data Index: 523972 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6907. Min Act: -0.0001

Data Index: 699135 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6895. Min Act: -0.0001

Data Index: 1190872 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6324. Min Act: -0.0001

Data Index: 407660 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6488. Min Act: -0.0001

Data Index: 278222 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6436. Min Act: -0.0001

Data Index: 891970 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6492. Min Act: -0.0001

Data Index: 562770 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6287. Min Act: -0.0001

Data Index: 591330 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5595. Min Act: -0.0001

Data Index: 529880 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6199. Min Act: -0.0001

Data Index: 349968 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5760. Min Act: -0.0001

Data Index: 1037952 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6158. Min Act: -0.0001

Data Index: 578167 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6130. Min Act: -0.0001

Data Index: 699439 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5569. Min Act: -0.0001

Data Index: 678806 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6270. Min Act: -0.0001

Data Index: 842029 (C4 (Web Text))

Max Activating Token Index: 515