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

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

Neuron 562 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: 0.8561. Min Range: -0.8561

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1062259 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.8533. Min Act: -0.0000

Data Index: 149726 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1230122 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.7908. Min Act: -0.0000

Data Index: 353007 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.8060. Min Act: -0.0000

Data Index: 727626 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.7511. Min Act: -0.0000

Data Index: 620378 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.7489. Min Act: -0.0000

Data Index: 974519 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.7746. Min Act: -0.0000

Data Index: 500233 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6735. Min Act: -0.0000

Data Index: 70497 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1291431 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6887. Min Act: -0.0000

Data Index: 120818 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6548. Min Act: -0.0000

Data Index: 458560 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1333892 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6912. Min Act: -0.0000

Data Index: 205354 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6924. Min Act: -0.0000

Data Index: 716849 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6743. Min Act: -0.0000

Data Index: 983328 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1313584 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6403. Min Act: -0.0000

Data Index: 940784 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6598. Min Act: -0.0000

Data Index: 854477 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6404. Min Act: -0.0000

Data Index: 674460 (C4 (Web Text))

Max Activating Token Index: 847