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

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

Neuron 5041 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1345. Min Range: -3.1345

Max Act: 3.1343. Min Act: -0.0001

Data Index: 1211659 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 3.1345. Min Range: -3.1345

Max Act: 3.1345. Min Act: -0.0001

Data Index: 3851 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.1345. Min Range: -3.1345

Max Act: 3.0647. Min Act: -0.0001

Data Index: 1029033 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.6787. Min Act: -0.0001

Data Index: 958190 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.9130. Min Act: -0.0001

Data Index: 1213454 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.8845. Min Act: -0.0000

Data Index: 1195076 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.8626. Min Act: -0.0001

Data Index: 687151 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.7686. Min Act: -0.0000

Data Index: 856236 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.7533. Min Act: -0.0000

Data Index: 88245 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.7423. Min Act: -0.0001

Data Index: 730461 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.7101. Min Act: -0.0001

Data Index: 370869 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.7176. Min Act: -0.0001

Data Index: 543516 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.5754. Min Act: -0.0001

Data Index: 1090267 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.5667. Min Act: -0.0000

Data Index: 474517 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.5787. Min Act: -0.0001

Data Index: 377616 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.6808. Min Act: -0.0001

Data Index: 283259 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.6637. Min Act: -0.0000

Data Index: 166354 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.6539. Min Act: -0.0001

Data Index: 534605 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.7768. Min Act: -0.0000

Data Index: 244488 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.5194. Min Act: -0.0001

Data Index: 1008883 (C4 (Web Text))

Max Activating Token Index: 796