Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2998 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3958. Min Act: -0.0000

Data Index: 807339 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1842526 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1525061 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1848800 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1532285 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1798749 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1654191 (The Pile)

Max Activating Token Index: 999

Text #7

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3817. Min Act: -0.0000

Data Index: 76385 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3369. Min Act: -0.0000

Data Index: 228347 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3446. Min Act: -0.0000

Data Index: 879727 (The Pile)

Max Activating Token Index: 569

Text #10

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1855636 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1816435 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1133156 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3305. Min Act: -0.0000

Data Index: 697163 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1536386 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1872762 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1791438 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1399292 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1945696 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1336068 (The Pile)

Max Activating Token Index: 105