Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1050 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.4012. Min Act: -0.0001

Data Index: 269929 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3773. Min Act: -0.0001

Data Index: 749548 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3648. Min Act: -0.0001

Data Index: 578818 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3626. Min Act: -0.0001

Data Index: 932971 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2992. Min Act: -0.0001

Data Index: 287949 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3024. Min Act: -0.0001

Data Index: 342610 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3032. Min Act: -0.0001

Data Index: 224564 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2670. Min Act: -0.0001

Data Index: 812775 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2946. Min Act: -0.0001

Data Index: 297861 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2522. Min Act: -0.0001

Data Index: 404246 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2736. Min Act: -0.0001

Data Index: 671297 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2455. Min Act: -0.0001

Data Index: 122136 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2501. Min Act: -0.0001

Data Index: 736270 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2406. Min Act: -0.0001

Data Index: 1164522 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1339196 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2500. Min Act: -0.0001

Data Index: 548915 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1093181 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2497. Min Act: -0.0001

Data Index: 523056 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2416. Min Act: -0.0001

Data Index: 577130 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2417. Min Act: -0.0001

Data Index: 1212930 (C4 (Web Text))

Max Activating Token Index: 51