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

Dataset: The Pile

Neuron 3284 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1554455 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.2268. Min Act: -0.0000

Data Index: 563654 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.2135. Min Act: -0.0000

Data Index: 661736 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1906. Min Act: -0.0000

Data Index: 769547 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1993. Min Act: -0.0000

Data Index: 890045 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1992. Min Act: -0.0000

Data Index: 387196 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1950. Min Act: -0.0000

Data Index: 862084 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1960. Min Act: -0.0000

Data Index: 998454 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1444490 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.2158. Min Act: -0.0000

Data Index: 526342 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1951. Min Act: -0.0000

Data Index: 529517 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1430847 (The Pile)

Max Activating Token Index: 574

Text #12

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1301944 (The Pile)

Max Activating Token Index: 762

Text #13

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1208656 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1933. Min Act: -0.0000

Data Index: 216047 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1835852 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1790975 (The Pile)

Max Activating Token Index: 319

Text #17

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1863. Min Act: -0.0000

Data Index: 304958 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1791. Min Act: -0.0000

Data Index: 949507 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1730985 (The Pile)

Max Activating Token Index: 238