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

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

Neuron 3350 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5893. Min Act: -0.0000

Data Index: 707646 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1049639 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5278. Min Act: -0.0000

Data Index: 505733 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4982. Min Act: -0.0000

Data Index: 777745 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4983. Min Act: -0.0000

Data Index: 846102 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5052. Min Act: -0.0000

Data Index: 349769 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4978. Min Act: -0.0000

Data Index: 525025 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4930. Min Act: 0.0000

Data Index: 827787 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4813. Min Act: -0.0000

Data Index: 352258 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1098862 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4757. Min Act: -0.0000

Data Index: 201370 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4643. Min Act: -0.0000

Data Index: 859851 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4735. Min Act: -0.0000

Data Index: 505394 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1313307 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4662. Min Act: -0.0000

Data Index: 661189 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4671. Min Act: 0.0000

Data Index: 1153428 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1006303 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1984 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1132742 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4510. Min Act: -0.0000

Data Index: 863656 (C4 (Web Text))

Max Activating Token Index: 969