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

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

Neuron 3440 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: 3.4134. Min Range: -3.4134

Max Act: 3.4134. Min Act: -0.0001

Data Index: 1498405 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 3.4134. Min Range: -3.4134

Max Act: 3.0767. Min Act: -0.0001

Data Index: 1575213 (Python Code)

Max Activating Token Index: 436

Text #2

Max Range: 3.4134. Min Range: -3.4134

Max Act: 3.0617. Min Act: -0.0001

Data Index: 1473841 (Python Code)

Max Activating Token Index: 413

Text #3

Max Range: 3.4134. Min Range: -3.4134

Max Act: 3.0146. Min Act: -0.0001

Data Index: 1512288 (Python Code)

Max Activating Token Index: 787

Text #4

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.9426. Min Act: -0.0001

Data Index: 1360469 (Python Code)

Max Activating Token Index: 912

Text #5

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.6629. Min Act: -0.0001

Data Index: 1560902 (Python Code)

Max Activating Token Index: 175

Text #6

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.6849. Min Act: -0.0001

Data Index: 1583169 (Python Code)

Max Activating Token Index: 767

Text #7

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.7954. Min Act: -0.0001

Data Index: 1365032 (Python Code)

Max Activating Token Index: 263

Text #8

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.7708. Min Act: -0.0001

Data Index: 1529626 (Python Code)

Max Activating Token Index: 990

Text #9

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.7456. Min Act: -0.0001

Data Index: 1516451 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.7273. Min Act: -0.0001

Data Index: 1419617 (Python Code)

Max Activating Token Index: 956

Text #11

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.6644. Min Act: -0.0001

Data Index: 1518860 (Python Code)

Max Activating Token Index: 204

Text #12

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.5264. Min Act: -0.0001

Data Index: 1525976 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.6583. Min Act: -0.0001

Data Index: 1554911 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.6299. Min Act: -0.0001

Data Index: 1501224 (Python Code)

Max Activating Token Index: 650

Text #15

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.5179. Min Act: -0.0001

Data Index: 1489207 (Python Code)

Max Activating Token Index: 156

Text #16

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.5091. Min Act: -0.0001

Data Index: 1608691 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.5030. Min Act: -0.0001

Data Index: 1624469 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.5037. Min Act: -0.0001

Data Index: 1516313 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 3.4134. Min Range: -3.4134

Max Act: 2.3846. Min Act: -0.0001

Data Index: 1612397 (Python Code)

Max Activating Token Index: 259