Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3056 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.9489. Min Act: -0.0001

Data Index: 1483568 (Python Code)

Max Activating Token Index: 507

Text #1

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.9473. Min Act: -0.0001

Data Index: 1369443 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.9361. Min Act: -0.0001

Data Index: 1470359 (Python Code)

Max Activating Token Index: 655

Text #3

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.7488. Min Act: -0.0001

Data Index: 1599771 (Python Code)

Max Activating Token Index: 889

Text #4

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6826. Min Act: -0.0001

Data Index: 1649451 (Python Code)

Max Activating Token Index: 533

Text #5

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6940. Min Act: -0.0001

Data Index: 1643853 (Python Code)

Max Activating Token Index: 337

Text #6

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.7225. Min Act: -0.0001

Data Index: 1585884 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6387. Min Act: -0.0001

Data Index: 1637056 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6652. Min Act: -0.0001

Data Index: 1488697 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6026. Min Act: -0.0001

Data Index: 1484817 (Python Code)

Max Activating Token Index: 403

Text #10

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6490. Min Act: -0.0001

Data Index: 1538853 (Python Code)

Max Activating Token Index: 407

Text #11

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.7385. Min Act: -0.0001

Data Index: 1577489 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.5773. Min Act: -0.0001

Data Index: 1502870 (Python Code)

Max Activating Token Index: 932

Text #13

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.5833. Min Act: -0.0001

Data Index: 1616545 (Python Code)

Max Activating Token Index: 797

Text #14

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6124. Min Act: -0.0001

Data Index: 1411946 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.5958. Min Act: -0.0001

Data Index: 1494775 (Python Code)

Max Activating Token Index: 311

Text #16

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.5794. Min Act: -0.0001

Data Index: 1625304 (Python Code)

Max Activating Token Index: 922

Text #17

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6264. Min Act: -0.0001

Data Index: 1448035 (Python Code)

Max Activating Token Index: 259

Text #18

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.4486. Min Act: -0.0001

Data Index: 1591711 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.5242. Min Act: -0.0001

Data Index: 1563153 (Python Code)

Max Activating Token Index: 487