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

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

Neuron 3319 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5925. Min Act: -0.0000

Data Index: 9834 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4680. Min Act: -0.0000

Data Index: 87533 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4990. Min Act: -0.0000

Data Index: 407299 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4873. Min Act: -0.0000

Data Index: 131750 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4794. Min Act: -0.0000

Data Index: 407105 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4568. Min Act: -0.0000

Data Index: 389944 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4491. Min Act: -0.0000

Data Index: 745983 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1092984 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4416. Min Act: -0.0000

Data Index: 341746 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4381. Min Act: -0.0000

Data Index: 372285 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4539. Min Act: -0.0000

Data Index: 28742 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4826. Min Act: -0.0000

Data Index: 858309 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1008826 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4287. Min Act: -0.0000

Data Index: 324257 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1007351 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4400. Min Act: -0.0000

Data Index: 700565 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1111716 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4232. Min Act: -0.0000

Data Index: 783567 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1349855 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.3735. Min Act: -0.0000

Data Index: 289785 (C4 (Web Text))

Max Activating Token Index: 973