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

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

Neuron 3977 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: 0.6886. Min Range: -0.6886

Max Act: 0.6886. Min Act: -0.0000

Data Index: 394465 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.6786. Min Act: -0.0000

Data Index: 717678 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1092671 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.5475. Min Act: -0.0000

Data Index: 360509 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1057350 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1194769 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.5288. Min Act: -0.0000

Data Index: 896110 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.4128. Min Act: -0.0000

Data Index: 903622 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.4790. Min Act: -0.0000

Data Index: 489173 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1092608 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.4114. Min Act: -0.0000

Data Index: 96901 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3934. Min Act: -0.0000

Data Index: 714097 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3820. Min Act: -0.0000

Data Index: 711259 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3699. Min Act: -0.0000

Data Index: 328279 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3708. Min Act: -0.0000

Data Index: 117118 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3583. Min Act: -0.0000

Data Index: 321186 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3780. Min Act: -0.0000

Data Index: 71616 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3504. Min Act: 0.0000

Data Index: 188457 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1058493 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3719. Min Act: -0.0000

Data Index: 124768 (C4 (Web Text))

Max Activating Token Index: 318