Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2872 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0004

Data Index: 1388597 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0426. Min Act: -0.0004

Data Index: 1602657 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0408. Min Act: -0.0004

Data Index: 1084708 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0378. Min Act: -0.0004

Data Index: 17357 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0379. Min Act: -0.0004

Data Index: 815368 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0374. Min Act: -0.0004

Data Index: 665085 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0366. Min Act: -0.0004

Data Index: 1548548 (Python Code)

Max Activating Token Index: 932

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0364. Min Act: -0.0004

Data Index: 688069 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0353. Min Act: -0.0004

Data Index: 66015 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0350. Min Act: -0.0004

Data Index: 948963 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0354. Min Act: -0.0004

Data Index: 1029452 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0325. Min Act: -0.0004

Data Index: 1017301 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0330. Min Act: -0.0004

Data Index: 623972 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0313. Min Act: -0.0004

Data Index: 1515352 (Python Code)

Max Activating Token Index: 663

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0317. Min Act: -0.0004

Data Index: 311530 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0317. Min Act: -0.0004

Data Index: 1174496 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0304. Min Act: -0.0004

Data Index: 732302 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0307. Min Act: -0.0004

Data Index: 1265174 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0303. Min Act: -0.0004

Data Index: 318676 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0301. Min Act: -0.0004

Data Index: 335123 (C4 (Web Text))

Max Activating Token Index: 138