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

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

Neuron 3873 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1995. Min Act: -0.0001

Data Index: 1444129 (Python Code)

Max Activating Token Index: 249

Text #1

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.9409. Min Act: -0.0001

Data Index: 1577720 (Python Code)

Max Activating Token Index: 685

Text #2

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1510860 (Python Code)

Max Activating Token Index: 950

Text #3

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1476178 (Python Code)

Max Activating Token Index: 58

Text #4

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7835. Min Act: -0.0001

Data Index: 1360860 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1493983 (Python Code)

Max Activating Token Index: 151

Text #6

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.8087. Min Act: -0.0001

Data Index: 1650308 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7272. Min Act: -0.0001

Data Index: 1397836 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1448777 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7603. Min Act: -0.0001

Data Index: 1472546 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1588706 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1364123 (Python Code)

Max Activating Token Index: 514

Text #12

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1472461 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1410155 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1521352 (Python Code)

Max Activating Token Index: 558

Text #15

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.6858. Min Act: -0.0001

Data Index: 1415480 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.6461. Min Act: -0.0001

Data Index: 1378497 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.6558. Min Act: -0.0001

Data Index: 1504364 (Python Code)

Max Activating Token Index: 796

Text #18

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1510335 (Python Code)

Max Activating Token Index: 315

Text #19

Max Range: 1.1995. Min Range: -1.1995

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1448272 (Python Code)

Max Activating Token Index: 31