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

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

Neuron 5093 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: 6.2102. Min Range: -6.2102

Max Act: 6.0303. Min Act: -0.0000

Data Index: 329974 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 6.2102. Min Range: -6.2102

Max Act: 6.0052. Min Act: -0.0000

Data Index: 104374 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.9569. Min Act: -0.0000

Data Index: 289489 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 6.2102. Min Range: -6.2102

Max Act: 6.2102. Min Act: -0.0000

Data Index: 1114454 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.9988. Min Act: -0.0000

Data Index: 797985 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.7730. Min Act: -0.0000

Data Index: 44682 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.8374. Min Act: -0.0000

Data Index: 427248 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.2515. Min Act: -0.0000

Data Index: 760556 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.7855. Min Act: -0.0000

Data Index: 644309 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 6.2102. Min Range: -6.2102

Max Act: 6.1615. Min Act: -0.0000

Data Index: 525089 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.7819. Min Act: -0.0000

Data Index: 1329463 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.7633. Min Act: -0.0000

Data Index: 658541 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.4765. Min Act: -0.0000

Data Index: 669166 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.6359. Min Act: -0.0000

Data Index: 773841 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.4164. Min Act: -0.0000

Data Index: 917768 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.9607. Min Act: -0.0000

Data Index: 809854 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.5789. Min Act: -0.0000

Data Index: 349593 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.4339. Min Act: -0.0000

Data Index: 1338444 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.4236. Min Act: -0.0000

Data Index: 356539 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 6.2102. Min Range: -6.2102

Max Act: 5.4356. Min Act: -0.0000

Data Index: 497470 (C4 (Web Text))

Max Activating Token Index: 692