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

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

Neuron 1033 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: 0.6349. Min Range: -0.6349

Max Act: 0.6349. Min Act: -0.0000

Data Index: 471850 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5876. Min Act: -0.0000

Data Index: 603819 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5830. Min Act: -0.0000

Data Index: 70466 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5245. Min Act: -0.0000

Data Index: 197258 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1140206 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5198. Min Act: -0.0000

Data Index: 917327 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1026073 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1028074 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4835. Min Act: -0.0000

Data Index: 422666 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4528. Min Act: -0.0000

Data Index: 864069 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4451. Min Act: -0.0000

Data Index: 429753 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4740. Min Act: -0.0000

Data Index: 166655 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1221986 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4685. Min Act: -0.0000

Data Index: 224410 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4376. Min Act: -0.0000

Data Index: 180279 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4374. Min Act: -0.0000

Data Index: 64893 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4122. Min Act: -0.0000

Data Index: 972298 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4330. Min Act: -0.0000

Data Index: 68232 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4291. Min Act: -0.0000

Data Index: 689041 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4442. Min Act: -0.0000

Data Index: 357290 (C4 (Web Text))

Max Activating Token Index: 522