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

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

Neuron 877 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: 3.7935. Min Range: -3.7935

Max Act: 3.7935. Min Act: -0.0001

Data Index: 724636 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 3.7935. Min Range: -3.7935

Max Act: 3.7064. Min Act: -0.0001

Data Index: 117868 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 3.7935. Min Range: -3.7935

Max Act: 3.5912. Min Act: -0.0001

Data Index: 929562 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 3.7935. Min Range: -3.7935

Max Act: 3.5565. Min Act: -0.0001

Data Index: 734059 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 3.7935. Min Range: -3.7935

Max Act: 3.2756. Min Act: -0.0001

Data Index: 222164 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.9444. Min Act: -0.0001

Data Index: 770773 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 3.7935. Min Range: -3.7935

Max Act: 3.1578. Min Act: -0.0001

Data Index: 924723 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 3.7935. Min Range: -3.7935

Max Act: 3.1038. Min Act: -0.0001

Data Index: 1314358 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 3.7935. Min Range: -3.7935

Max Act: 3.0458. Min Act: -0.0001

Data Index: 439611 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.9475. Min Act: -0.0001

Data Index: 30134 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.8126. Min Act: -0.0001

Data Index: 694451 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 3.7935. Min Range: -3.7935

Max Act: 3.2244. Min Act: -0.0000

Data Index: 483317 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.9075. Min Act: -0.0001

Data Index: 338106 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.9261. Min Act: -0.0001

Data Index: 774421 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.6777. Min Act: -0.0001

Data Index: 88937 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.7554. Min Act: -0.0001

Data Index: 1181427 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.7495. Min Act: -0.0001

Data Index: 945765 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.8837. Min Act: -0.0001

Data Index: 585656 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.7417. Min Act: -0.0001

Data Index: 547208 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 3.7935. Min Range: -3.7935

Max Act: 2.7505. Min Act: -0.0001

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 115