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

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

Neuron 4521 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3529. Min Act: -0.0001

Data Index: 675880 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3566. Min Act: -0.0001

Data Index: 753047 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3452. Min Act: -0.0001

Data Index: 467870 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3376. Min Act: -0.0001

Data Index: 555046 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3494. Min Act: -0.0001

Data Index: 1341300 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3472. Min Act: -0.0001

Data Index: 178830 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3448. Min Act: -0.0001

Data Index: 375057 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3394. Min Act: -0.0001

Data Index: 549478 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3343. Min Act: -0.0001

Data Index: 798950 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3478. Min Act: -0.0001

Data Index: 164071 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3206. Min Act: -0.0001

Data Index: 536942 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3232. Min Act: -0.0001

Data Index: 435693 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3258. Min Act: -0.0001

Data Index: 1049632 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3332. Min Act: -0.0001

Data Index: 943815 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1043490 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3189. Min Act: -0.0001

Data Index: 72901 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3183. Min Act: -0.0001

Data Index: 48669 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3402. Min Act: -0.0001

Data Index: 1129974 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3252. Min Act: -0.0001

Data Index: 342791 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3222. Min Act: -0.0001

Data Index: 1080235 (C4 (Web Text))

Max Activating Token Index: 470