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

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

Neuron 516 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.4538. Min Act: -0.0000

Data Index: 70506 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3909. Min Act: -0.0000

Data Index: 508545 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3624. Min Act: -0.0000

Data Index: 469904 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3505. Min Act: 0.0000

Data Index: 790599 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3470. Min Act: -0.0000

Data Index: 19438 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1045399 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3419. Min Act: -0.0000

Data Index: 697002 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1262654 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3385. Min Act: 0.0000

Data Index: 568438 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1065441 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3253. Min Act: 0.0001

Data Index: 106104 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3372. Min Act: -0.0000

Data Index: 657921 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3217. Min Act: -0.0000

Data Index: 123943 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3299. Min Act: -0.0000

Data Index: 999170 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3407. Min Act: -0.0001

Data Index: 547161 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3199. Min Act: -0.0001

Data Index: 799938 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3177. Min Act: -0.0001

Data Index: 4853 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3134. Min Act: -0.0001

Data Index: 25182 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3111. Min Act: -0.0000

Data Index: 451057 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3011. Min Act: -0.0000

Data Index: 310453 (C4 (Web Text))

Max Activating Token Index: 203