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

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

Neuron 1535 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.9191. Min Act: -0.0001

Data Index: 451889 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.9457. Min Act: -0.0001

Data Index: 1322457 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.8605. Min Act: -0.0001

Data Index: 1357772 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7671. Min Act: -0.0001

Data Index: 655964 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7716. Min Act: -0.0001

Data Index: 1035752 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7930. Min Act: -0.0001

Data Index: 1055924 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7691. Min Act: -0.0001

Data Index: 998595 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7444. Min Act: -0.0001

Data Index: 1126183 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1054384 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7267. Min Act: -0.0001

Data Index: 1319242 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7454. Min Act: -0.0001

Data Index: 929683 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7627. Min Act: -0.0001

Data Index: 1061305 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7378. Min Act: -0.0001

Data Index: 609029 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7269. Min Act: -0.0001

Data Index: 235897 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7006. Min Act: -0.0001

Data Index: 223981 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7388. Min Act: -0.0001

Data Index: 175783 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7126. Min Act: -0.0001

Data Index: 517693 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.6819. Min Act: -0.0001

Data Index: 1046500 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7042. Min Act: -0.0001

Data Index: 98164 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.6999. Min Act: -0.0001

Data Index: 433717 (C4 (Web Text))

Max Activating Token Index: 256