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

Dataset: The Pile

Neuron 2666 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: 3.8449. Min Range: -3.8449

Max Act: 3.8449. Min Act: -0.0000

Data Index: 1918749 (The Pile)

Max Activating Token Index: 428

Text #1

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.5827. Min Act: -0.0000

Data Index: 307897 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.6395. Min Act: -0.0000

Data Index: 408402 (The Pile)

Max Activating Token Index: 636

Text #3

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.6213. Min Act: -0.0000

Data Index: 1395198 (The Pile)

Max Activating Token Index: 298

Text #4

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.6873. Min Act: -0.0000

Data Index: 684740 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.1694. Min Act: -0.0000

Data Index: 200968 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.1285. Min Act: -0.0000

Data Index: 31628 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.2680. Min Act: -0.0000

Data Index: 196128 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.0454. Min Act: -0.0000

Data Index: 507263 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.1353. Min Act: -0.0000

Data Index: 873225 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 3.8449. Min Range: -3.8449

Max Act: 2.9614. Min Act: -0.0000

Data Index: 1891267 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 3.8449. Min Range: -3.8449

Max Act: 2.9545. Min Act: -0.0000

Data Index: 443590 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.1111. Min Act: -0.0000

Data Index: 1969109 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.0793. Min Act: -0.0000

Data Index: 679924 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 3.8449. Min Range: -3.8449

Max Act: 3.2132. Min Act: -0.0000

Data Index: 41901 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 3.8449. Min Range: -3.8449

Max Act: 2.7270. Min Act: -0.0000

Data Index: 650699 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 3.8449. Min Range: -3.8449

Max Act: 2.7172. Min Act: -0.0000

Data Index: 1801605 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 3.8449. Min Range: -3.8449

Max Act: 2.8312. Min Act: -0.0000

Data Index: 1371819 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 3.8449. Min Range: -3.8449

Max Act: 2.6620. Min Act: -0.0000

Data Index: 274767 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 3.8449. Min Range: -3.8449

Max Act: 2.7791. Min Act: -0.0000

Data Index: 243250 (The Pile)

Max Activating Token Index: 322