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

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

Neuron 4226 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4665. Min Range: -1.4665

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1149358 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.4665. Min Range: -1.4665

Max Act: 1.2964. Min Act: -0.0000

Data Index: 569271 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.4665. Min Range: -1.4665

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1490826 (Python Code)

Max Activating Token Index: 57

Text #3

Max Range: 1.4665. Min Range: -1.4665

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1337409 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.9754. Min Act: -0.0000

Data Index: 986842 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 1.4665. Min Range: -1.4665

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1347691 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.9594. Min Act: -0.0000

Data Index: 754687 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.9930. Min Act: -0.0001

Data Index: 4094 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 1.4665. Min Range: -1.4665

Max Act: 1.1215. Min Act: -0.0000

Data Index: 475585 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1547901 (Python Code)

Max Activating Token Index: 651

Text #10

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.9625. Min Act: -0.0000

Data Index: 746239 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1376644 (Python Code)

Max Activating Token Index: 594

Text #12

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1034732 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.8408. Min Act: -0.0000

Data Index: 920883 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.8547. Min Act: -0.0000

Data Index: 972333 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.8752. Min Act: -0.0000

Data Index: 807553 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.8499. Min Act: -0.0001

Data Index: 537604 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.8075. Min Act: -0.0000

Data Index: 357711 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.7399. Min Act: -0.0001

Data Index: 1215217 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.4665. Min Range: -1.4665

Max Act: 0.8528. Min Act: -0.0000

Data Index: 131966 (C4 (Web Text))

Max Activating Token Index: 579