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

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

Neuron 1969 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.7522. Min Act: -0.0001

Data Index: 1530806 (Python Code)

Max Activating Token Index: 953

Text #1

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.7238. Min Act: -0.0001

Data Index: 1535955 (Python Code)

Max Activating Token Index: 393

Text #2

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.7254. Min Act: -0.0001

Data Index: 1622258 (Python Code)

Max Activating Token Index: 641

Text #3

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1410641 (Python Code)

Max Activating Token Index: 998

Text #4

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6996. Min Act: -0.0001

Data Index: 1398685 (Python Code)

Max Activating Token Index: 1012

Text #5

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6701. Min Act: -0.0001

Data Index: 1469014 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6627. Min Act: -0.0001

Data Index: 1414826 (Python Code)

Max Activating Token Index: 1003

Text #7

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6752. Min Act: -0.0001

Data Index: 1437454 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6459. Min Act: -0.0001

Data Index: 1606337 (Python Code)

Max Activating Token Index: 79

Text #9

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6365. Min Act: -0.0001

Data Index: 1422435 (Python Code)

Max Activating Token Index: 395

Text #10

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6318. Min Act: -0.0001

Data Index: 1476196 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6643. Min Act: -0.0001

Data Index: 1388737 (Python Code)

Max Activating Token Index: 316

Text #12

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6427. Min Act: -0.0001

Data Index: 1550000 (Python Code)

Max Activating Token Index: 589

Text #13

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6337. Min Act: -0.0001

Data Index: 1400321 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6523. Min Act: -0.0001

Data Index: 1473693 (Python Code)

Max Activating Token Index: 310

Text #15

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6241. Min Act: -0.0001

Data Index: 1513341 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6846. Min Act: -0.0001

Data Index: 1500740 (Python Code)

Max Activating Token Index: 777

Text #17

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6114. Min Act: -0.0001

Data Index: 1589879 (Python Code)

Max Activating Token Index: 897

Text #18

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1656130 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6390. Min Act: -0.0001

Data Index: 1510452 (Python Code)

Max Activating Token Index: 710