Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2013 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0072. Min Range: -2.0072

Max Act: 2.0072. Min Act: -0.0000

Data Index: 867987 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.4596. Min Act: -0.0000

Data Index: 47135 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1306515 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3556. Min Act: -0.0000

Data Index: 752706 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3511. Min Act: -0.0000

Data Index: 338338 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3929. Min Act: -0.0000

Data Index: 367839 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2434. Min Act: -0.0000

Data Index: 346567 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1661. Min Act: -0.0000

Data Index: 183416 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1218185 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1244318 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1210. Min Act: -0.0000

Data Index: 620875 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1488. Min Act: -0.0000

Data Index: 723946 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1452. Min Act: -0.0000

Data Index: 571789 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1446. Min Act: -0.0000

Data Index: 183971 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1336. Min Act: -0.0000

Data Index: 353668 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.0591. Min Act: -0.0000

Data Index: 962122 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1954. Min Act: -0.0000

Data Index: 660758 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1242. Min Act: -0.0000

Data Index: 228193 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.0506. Min Act: -0.0000

Data Index: 963642 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1034. Min Act: -0.0000

Data Index: 819571 (C4 (Web Text))

Max Activating Token Index: 81