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

Dataset: The Pile

Neuron 2754 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3844. Min Act: -0.0000

Data Index: 421169 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3015. Min Act: -0.0000

Data Index: 515027 (The Pile)

Max Activating Token Index: 549

Text #2

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1294903 (The Pile)

Max Activating Token Index: 278

Text #3

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1287045 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1524255 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1798220 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2907. Min Act: 0.0000

Data Index: 1882444 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1209953 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1709296 (The Pile)

Max Activating Token Index: 827

Text #9

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2681. Min Act: -0.0000

Data Index: 290741 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1262574 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2640. Min Act: 0.0000

Data Index: 1530761 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1130259 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2517. Min Act: 0.0000

Data Index: 328140 (The Pile)

Max Activating Token Index: 373

Text #14

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2506. Min Act: -0.0000

Data Index: 479376 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2498. Min Act: -0.0000

Data Index: 161683 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2531. Min Act: 0.0000

Data Index: 1874130 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1436424 (The Pile)

Max Activating Token Index: 39

Text #18

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1223524 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1103934 (The Pile)

Max Activating Token Index: 651