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

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

Neuron 3411 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1265763 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0492. Min Act: -0.0002

Data Index: 759609 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0495. Min Act: -0.0002

Data Index: 208656 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0482. Min Act: -0.0002

Data Index: 912165 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0475. Min Act: -0.0002

Data Index: 285747 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0498. Min Act: -0.0002

Data Index: 178572 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0470. Min Act: -0.0002

Data Index: 73250 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1335981 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0472. Min Act: -0.0002

Data Index: 149581 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0400. Min Act: -0.0002

Data Index: 260070 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0458. Min Act: -0.0002

Data Index: 902243 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0409. Min Act: -0.0002

Data Index: 585153 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0425. Min Act: -0.0002

Data Index: 192599 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0430. Min Act: -0.0002

Data Index: 278912 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0428. Min Act: -0.0002

Data Index: 853445 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0445. Min Act: -0.0002

Data Index: 358144 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0450. Min Act: -0.0002

Data Index: 683379 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0460. Min Act: -0.0002

Data Index: 336032 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0429. Min Act: -0.0002

Data Index: 354057 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0419. Min Act: -0.0002

Data Index: 391702 (C4 (Web Text))

Max Activating Token Index: 341