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

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

Neuron 3980 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: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0001

Data Index: 51075 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0591. Min Act: -0.0001

Data Index: 946968 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0567. Min Act: -0.0001

Data Index: 131065 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0563. Min Act: -0.0001

Data Index: 309315 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1259789 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0555. Min Act: -0.0001

Data Index: 657262 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0544. Min Act: -0.0001

Data Index: 837981 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0556. Min Act: -0.0001

Data Index: 479314 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0536. Min Act: -0.0001

Data Index: 988243 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1382385 (Python Code)

Max Activating Token Index: 715

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0531. Min Act: -0.0001

Data Index: 933681 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0525. Min Act: -0.0001

Data Index: 935573 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0522. Min Act: -0.0001

Data Index: 697837 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0513. Min Act: -0.0001

Data Index: 719343 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1199867 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0507. Min Act: -0.0001

Data Index: 940508 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0500. Min Act: -0.0001

Data Index: 697598 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0489. Min Act: -0.0001

Data Index: 673995 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0477. Min Act: -0.0001

Data Index: 640240 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0485. Min Act: -0.0001

Data Index: 593320 (C4 (Web Text))

Max Activating Token Index: 501