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

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

Neuron 3528 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.8813. Min Act: -0.0001

Data Index: 216132 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7929. Min Act: -0.0001

Data Index: 329334 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.8273. Min Act: -0.0001

Data Index: 242480 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7368. Min Act: -0.0001

Data Index: 619460 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7393. Min Act: -0.0001

Data Index: 595000 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7870. Min Act: -0.0001

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7189. Min Act: -0.0001

Data Index: 540208 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7014. Min Act: -0.0001

Data Index: 131746 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6745. Min Act: -0.0001

Data Index: 717674 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6726. Min Act: -0.0001

Data Index: 611626 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6878. Min Act: -0.0001

Data Index: 715873 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6874. Min Act: -0.0001

Data Index: 13140 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6824. Min Act: -0.0001

Data Index: 548899 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6489. Min Act: -0.0001

Data Index: 363959 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6903. Min Act: -0.0001

Data Index: 1242301 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6430. Min Act: -0.0001

Data Index: 626765 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6819. Min Act: -0.0001

Data Index: 495104 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6988. Min Act: -0.0001

Data Index: 1303184 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6693. Min Act: -0.0001

Data Index: 879807 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6279. Min Act: -0.0001

Data Index: 250359 (C4 (Web Text))

Max Activating Token Index: 743