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

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

Neuron 962 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.6652. Min Act: -0.0001

Data Index: 633972 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.5171. Min Act: -0.0001

Data Index: 1193148 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.5099. Min Act: -0.0001

Data Index: 184312 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.5628. Min Act: -0.0001

Data Index: 632831 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4618. Min Act: -0.0001

Data Index: 1301377 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4713. Min Act: -0.0001

Data Index: 689421 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4793. Min Act: -0.0001

Data Index: 292422 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4570. Min Act: -0.0001

Data Index: 1023138 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3156. Min Act: -0.0001

Data Index: 382697 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3985. Min Act: -0.0001

Data Index: 1037680 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4258. Min Act: -0.0001

Data Index: 455902 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4489. Min Act: -0.0001

Data Index: 213142 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4123. Min Act: -0.0001

Data Index: 289406 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4757. Min Act: -0.0001

Data Index: 1197749 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3576. Min Act: -0.0001

Data Index: 178197 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3430. Min Act: -0.0001

Data Index: 571121 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3697. Min Act: -0.0001

Data Index: 488621 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3263. Min Act: -0.0001

Data Index: 1028951 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3541. Min Act: -0.0001

Data Index: 1537 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3611. Min Act: -0.0001

Data Index: 414496 (C4 (Web Text))

Max Activating Token Index: 779