Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 97 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0003

Data Index: 114323 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0461. Min Act: -0.0003

Data Index: 648662 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0410. Min Act: -0.0004

Data Index: 381503 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0385. Min Act: -0.0003

Data Index: 126601 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1058416 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0371. Min Act: -0.0003

Data Index: 389667 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1497663 (Python Code)

Max Activating Token Index: 603

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0351. Min Act: -0.0003

Data Index: 42269 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0321. Min Act: -0.0003

Data Index: 996669 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1588049 (Python Code)

Max Activating Token Index: 748

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1003310 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0328. Min Act: -0.0002

Data Index: 974226 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1466116 (Python Code)

Max Activating Token Index: 791

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0327. Min Act: -0.0004

Data Index: 551805 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1554244 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0318. Min Act: -0.0003

Data Index: 752556 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0311. Min Act: -0.0003

Data Index: 980001 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1007589 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0304. Min Act: -0.0003

Data Index: 346586 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1611891 (Python Code)

Max Activating Token Index: 753