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

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

Neuron 2542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6799. Min Act: -0.0001

Data Index: 552735 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6516. Min Act: -0.0001

Data Index: 1000222 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6650. Min Act: -0.0001

Data Index: 564638 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6534. Min Act: -0.0001

Data Index: 288971 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6019. Min Act: -0.0001

Data Index: 393803 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5736. Min Act: -0.0001

Data Index: 1445353 (Python Code)

Max Activating Token Index: 781

Text #6

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1252232 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6034. Min Act: -0.0001

Data Index: 885263 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6011. Min Act: -0.0001

Data Index: 1297695 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5611. Min Act: -0.0001

Data Index: 986221 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.4685. Min Act: -0.0001

Data Index: 524905 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5167. Min Act: -0.0001

Data Index: 847417 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5114. Min Act: -0.0001

Data Index: 1205587 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5212. Min Act: -0.0001

Data Index: 749883 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5226. Min Act: -0.0001

Data Index: 1024068 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5195. Min Act: -0.0001

Data Index: 88118 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.4932. Min Act: -0.0001

Data Index: 826702 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.4884. Min Act: -0.0001

Data Index: 429914 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5096. Min Act: -0.0001

Data Index: 585541 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.4722. Min Act: -0.0001

Data Index: 128132 (C4 (Web Text))

Max Activating Token Index: 801