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

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

Neuron 4275 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1644136 (Python Code)

Max Activating Token Index: 891

Text #1

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1629784 (Python Code)

Max Activating Token Index: 390

Text #2

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2857. Min Act: -0.0000

Data Index: 1559538 (Python Code)

Max Activating Token Index: 455

Text #3

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1471588 (Python Code)

Max Activating Token Index: 403

Text #4

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2378. Min Act: -0.0000

Data Index: 440134 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1598623 (Python Code)

Max Activating Token Index: 196

Text #6

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1440492 (Python Code)

Max Activating Token Index: 166

Text #7

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2326. Min Act: -0.0000

Data Index: 703808 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2199. Min Act: -0.0000

Data Index: 645471 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1655122 (Python Code)

Max Activating Token Index: 717

Text #10

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2155. Min Act: 0.0000

Data Index: 1610130 (Python Code)

Max Activating Token Index: 283

Text #11

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2145. Min Act: -0.0000

Data Index: 335211 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2128. Min Act: -0.0000

Data Index: 569278 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2073. Min Act: -0.0000

Data Index: 910806 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.1944. Min Act: -0.0000

Data Index: 870353 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1515628 (Python Code)

Max Activating Token Index: 657

Text #16

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1572634 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.1960. Min Act: -0.0000

Data Index: 713590 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2041. Min Act: -0.0000

Data Index: 87347 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1604055 (Python Code)

Max Activating Token Index: 99