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

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

Neuron 3158 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6346. Min Act: -0.0001

Data Index: 626201 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5799. Min Act: -0.0001

Data Index: 729095 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6023. Min Act: -0.0001

Data Index: 812685 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5457. Min Act: -0.0001

Data Index: 191063 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5363. Min Act: -0.0001

Data Index: 689910 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5209. Min Act: -0.0001

Data Index: 346706 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5241. Min Act: -0.0001

Data Index: 1230885 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5138. Min Act: -0.0001

Data Index: 306921 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4859. Min Act: -0.0001

Data Index: 1218449 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4916. Min Act: -0.0001

Data Index: 418449 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4907. Min Act: -0.0001

Data Index: 468244 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5070. Min Act: -0.0001

Data Index: 794544 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4886. Min Act: -0.0001

Data Index: 28137 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5226. Min Act: -0.0001

Data Index: 1243105 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4871. Min Act: -0.0001

Data Index: 678276 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4991. Min Act: -0.0001

Data Index: 465643 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4756. Min Act: -0.0001

Data Index: 18041 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4766. Min Act: -0.0001

Data Index: 30533 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4610. Min Act: -0.0001

Data Index: 594219 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4715. Min Act: -0.0001

Data Index: 313414 (C4 (Web Text))

Max Activating Token Index: 747