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

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

Neuron 4494 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4842. Min Act: -0.0001

Data Index: 73384 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4939. Min Act: -0.0001

Data Index: 12856 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.5012. Min Act: -0.0001

Data Index: 184197 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4481. Min Act: -0.0001

Data Index: 9413 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4484. Min Act: -0.0001

Data Index: 1056529 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3907. Min Act: -0.0001

Data Index: 511471 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3662. Min Act: -0.0001

Data Index: 350272 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3766. Min Act: -0.0001

Data Index: 403813 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3574. Min Act: -0.0001

Data Index: 256867 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3607. Min Act: -0.0001

Data Index: 636409 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3573. Min Act: -0.0001

Data Index: 1092175 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3514. Min Act: -0.0001

Data Index: 232441 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3544. Min Act: -0.0001

Data Index: 823023 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1054858 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3599. Min Act: -0.0001

Data Index: 86920 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3242. Min Act: -0.0001

Data Index: 684005 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3342. Min Act: -0.0001

Data Index: 715596 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3246. Min Act: -0.0001

Data Index: 548882 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3481. Min Act: -0.0001

Data Index: 51162 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3446. Min Act: -0.0001

Data Index: 765566 (C4 (Web Text))

Max Activating Token Index: 916