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

Dataset: The Pile

Neuron 2253 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0461. Min Act: -0.0000

Data Index: 87450 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0456. Min Act: -0.0000

Data Index: 201667 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1024916 (The Pile)

Max Activating Token Index: 52

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0447. Min Act: -0.0000

Data Index: 994994 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0439. Min Act: -0.0000

Data Index: 486307 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1143290 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0438. Min Act: -0.0000

Data Index: 968776 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0437. Min Act: -0.0000

Data Index: 1837102 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0436. Min Act: -0.0000

Data Index: 628077 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0434. Min Act: -0.0000

Data Index: 74672 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0417. Min Act: -0.0000

Data Index: 1518624 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1193148 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0426. Min Act: -0.0000

Data Index: 645049 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0422. Min Act: -0.0000

Data Index: 1856368 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0408. Min Act: -0.0000

Data Index: 1820691 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0421. Min Act: -0.0000

Data Index: 102115 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1071368 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0435. Min Act: -0.0000

Data Index: 1087859 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0418. Min Act: -0.0000

Data Index: 1211584 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1013904 (The Pile)

Max Activating Token Index: 858