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

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

Neuron 2385 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1133384 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1354179 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0505. Min Act: -0.0001

Data Index: 794523 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0488. Min Act: -0.0001

Data Index: 371561 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1134931 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0493. Min Act: -0.0001

Data Index: 939687 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0506. Min Act: -0.0001

Data Index: 915128 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0447. Min Act: -0.0001

Data Index: 20293 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1351247 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0468. Min Act: -0.0001

Data Index: 932917 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0451. Min Act: -0.0001

Data Index: 176186 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0444. Min Act: -0.0001

Data Index: 373671 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0421. Min Act: -0.0001

Data Index: 340922 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0442. Min Act: -0.0001

Data Index: 899338 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0448. Min Act: -0.0001

Data Index: 860871 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0393. Min Act: -0.0001

Data Index: 81993 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0417. Min Act: -0.0001

Data Index: 516546 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0416. Min Act: -0.0001

Data Index: 819737 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0408. Min Act: -0.0001

Data Index: 209306 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1042446 (C4 (Web Text))

Max Activating Token Index: 434