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

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

Neuron 4339 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.7955. Min Act: -0.0000

Data Index: 1113310 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.5920. Min Act: -0.0000

Data Index: 524441 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.4352. Min Act: -0.0000

Data Index: 140492 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.4332. Min Act: -0.0000

Data Index: 455262 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1261767 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.3135. Min Act: -0.0000

Data Index: 1125392 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.3185. Min Act: -0.0000

Data Index: 892669 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.4450. Min Act: -0.0000

Data Index: 353345 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.3489. Min Act: -0.0000

Data Index: 447596 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1447. Min Act: -0.0000

Data Index: 291252 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.2382. Min Act: -0.0000

Data Index: 649224 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.2525. Min Act: -0.0000

Data Index: 422058 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1859. Min Act: -0.0000

Data Index: 944549 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1389. Min Act: -0.0000

Data Index: 232096 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1069190 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.0776. Min Act: -0.0000

Data Index: 289543 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1494. Min Act: -0.0000

Data Index: 421546 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1470. Min Act: -0.0000

Data Index: 1135138 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1051. Min Act: -0.0000

Data Index: 677769 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1283302 (C4 (Web Text))

Max Activating Token Index: 740