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

Dataset: The Pile

Neuron 2696 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1433885 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0573. Min Act: -0.0000

Data Index: 743028 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1325. Min Act: -0.0000

Data Index: 695075 (The Pile)

Max Activating Token Index: 896

Text #3

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0363. Min Act: -0.0000

Data Index: 1223471 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0062. Min Act: -0.0000

Data Index: 787051 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1568782 (The Pile)

Max Activating Token Index: 472

Text #6

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0125. Min Act: -0.0000

Data Index: 64499 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1518493 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1657552 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9090. Min Act: -0.0000

Data Index: 730859 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0375. Min Act: -0.0000

Data Index: 59764 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.7798. Min Act: -0.0000

Data Index: 644809 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9457. Min Act: -0.0000

Data Index: 1293830 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1382322 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1036180 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1478968 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1283559 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1729352 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1904648 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 1.1325. Min Range: -1.1325

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1162512 (The Pile)

Max Activating Token Index: 659