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

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

Neuron 3097 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.2491. Min Range: -10.2491

Max Act: 10.2491. Min Act: -0.0000

Data Index: 621857 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 10.2491. Min Range: -10.2491

Max Act: 9.2487. Min Act: -0.0000

Data Index: 127745 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 10.2491. Min Range: -10.2491

Max Act: 9.0994. Min Act: -0.0000

Data Index: 1044260 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 10.2491. Min Range: -10.2491

Max Act: 8.0816. Min Act: -0.0000

Data Index: 902419 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 10.2491. Min Range: -10.2491

Max Act: 7.2850. Min Act: -0.0000

Data Index: 491057 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 10.2491. Min Range: -10.2491

Max Act: 7.0190. Min Act: -0.0000

Data Index: 359388 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.9660. Min Act: -0.0000

Data Index: 239995 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.9678. Min Act: -0.0000

Data Index: 149729 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 10.2491. Min Range: -10.2491

Max Act: 7.1523. Min Act: -0.0000

Data Index: 505706 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.7393. Min Act: -0.0000

Data Index: 33204 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.6065. Min Act: -0.0000

Data Index: 1132550 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.5703. Min Act: -0.0000

Data Index: 782926 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.7481. Min Act: -0.0000

Data Index: 545176 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.5494. Min Act: -0.0000

Data Index: 1054103 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.4895. Min Act: -0.0000

Data Index: 433785 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.4062. Min Act: -0.0000

Data Index: 152366 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.5620. Min Act: -0.0000

Data Index: 480730 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.4148. Min Act: -0.0000

Data Index: 112242 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.3346. Min Act: -0.0000

Data Index: 849006 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 10.2491. Min Range: -10.2491

Max Act: 6.5016. Min Act: -0.0000

Data Index: 771713 (C4 (Web Text))

Max Activating Token Index: 950