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

Dataset: The Pile

Neuron 2997 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7258. Min Range: -7.7258

Max Act: 7.7258. Min Act: -0.0000

Data Index: 1455091 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 7.7258. Min Range: -7.7258

Max Act: 5.9568. Min Act: -0.0000

Data Index: 1656622 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 7.7258. Min Range: -7.7258

Max Act: 6.0821. Min Act: -0.0000

Data Index: 964420 (The Pile)

Max Activating Token Index: 278

Text #3

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.6389. Min Act: -0.0000

Data Index: 1513539 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.8436. Min Act: -0.0000

Data Index: 514349 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.5554. Min Act: -0.0000

Data Index: 1110820 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 7.7258. Min Range: -7.7258

Max Act: 3.9938. Min Act: -0.0000

Data Index: 1604238 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.7739. Min Act: -0.0000

Data Index: 1997033 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.4654. Min Act: -0.0000

Data Index: 1094737 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.5028. Min Act: -0.0000

Data Index: 1701751 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.1499. Min Act: -0.0000

Data Index: 666655 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.3944. Min Act: -0.0000

Data Index: 1476612 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.2323. Min Act: -0.0000

Data Index: 1916469 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.1477. Min Act: -0.0000

Data Index: 1877300 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.6819. Min Act: -0.0000

Data Index: 1190250 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 7.7258. Min Range: -7.7258

Max Act: 4.9143. Min Act: -0.0000

Data Index: 160550 (The Pile)

Max Activating Token Index: 502

Text #16

Max Range: 7.7258. Min Range: -7.7258

Max Act: 3.5166. Min Act: -0.0000

Data Index: 584204 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 7.7258. Min Range: -7.7258

Max Act: 3.6978. Min Act: -0.0000

Data Index: 1661307 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 7.7258. Min Range: -7.7258

Max Act: 3.7022. Min Act: -0.0000

Data Index: 1047812 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 7.7258. Min Range: -7.7258

Max Act: 3.8052. Min Act: -0.0000

Data Index: 1137421 (The Pile)

Max Activating Token Index: 621