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

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

Neuron 2487 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2728. Min Act: -0.0001

Data Index: 480529 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2553. Min Act: -0.0001

Data Index: 826370 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2486. Min Act: -0.0001

Data Index: 50925 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2461. Min Act: -0.0001

Data Index: 1337960 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2337. Min Act: -0.0001

Data Index: 789502 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2153. Min Act: -0.0001

Data Index: 245946 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1322812 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2223. Min Act: -0.0001

Data Index: 857909 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1958. Min Act: -0.0001

Data Index: 558280 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2048. Min Act: -0.0001

Data Index: 696123 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1294534 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2017. Min Act: -0.0001

Data Index: 1009735 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1924. Min Act: -0.0001

Data Index: 1247009 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1007283 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1824. Min Act: -0.0001

Data Index: 997260 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1847. Min Act: -0.0001

Data Index: 255789 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1867. Min Act: -0.0001

Data Index: 605462 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1916. Min Act: -0.0001

Data Index: 397674 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1850. Min Act: -0.0001

Data Index: 87755 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1924. Min Act: -0.0001

Data Index: 291114 (C4 (Web Text))

Max Activating Token Index: 992