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

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

Neuron 2485 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: 0.7323. Min Range: -0.7323

Max Act: 0.7323. Min Act: -0.0001

Data Index: 371918 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5177. Min Act: -0.0001

Data Index: 257656 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5093. Min Act: -0.0001

Data Index: 782433 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5054. Min Act: -0.0001

Data Index: 412470 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5088. Min Act: -0.0001

Data Index: 151340 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4565. Min Act: -0.0001

Data Index: 369104 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4702. Min Act: -0.0001

Data Index: 81565 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4893. Min Act: -0.0001

Data Index: 658685 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4661. Min Act: -0.0001

Data Index: 477668 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4670. Min Act: -0.0001

Data Index: 1024157 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4505. Min Act: -0.0001

Data Index: 867796 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4509. Min Act: -0.0001

Data Index: 825527 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4243. Min Act: -0.0001

Data Index: 881106 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4695. Min Act: -0.0001

Data Index: 144156 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4911. Min Act: -0.0001

Data Index: 853553 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4416. Min Act: -0.0001

Data Index: 226200 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4532. Min Act: -0.0001

Data Index: 572560 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4191. Min Act: -0.0001

Data Index: 555698 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4362. Min Act: -0.0001

Data Index: 628112 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4183. Min Act: -0.0001

Data Index: 1281580 (C4 (Web Text))

Max Activating Token Index: 746