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

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

Neuron 382 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0510. Min Act: -0.0001

Data Index: 130587 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0517. Min Act: -0.0001

Data Index: 481668 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1345778 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0496. Min Act: -0.0000

Data Index: 410054 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1298974 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0468. Min Act: -0.0001

Data Index: 503290 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1304909 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1041777 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0442. Min Act: -0.0001

Data Index: 236360 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1240419 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1387392 (Python Code)

Max Activating Token Index: 819

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1576356 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0448. Min Act: -0.0001

Data Index: 593837 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0483. Min Act: -0.0001

Data Index: 866940 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0408. Min Act: -0.0001

Data Index: 477042 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0441. Min Act: -0.0001

Data Index: 738587 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0451. Min Act: -0.0001

Data Index: 81649 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0446. Min Act: -0.0001

Data Index: 313847 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0414. Min Act: -0.0001

Data Index: 880111 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0414. Min Act: -0.0000

Data Index: 1448770 (Python Code)

Max Activating Token Index: 979