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

Dataset: The Pile

Neuron 525 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: 0.6086. Min Range: -0.6086

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1368094 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1141130 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.5064. Min Act: -0.0000

Data Index: 326604 (The Pile)

Max Activating Token Index: 851

Text #3

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.5737. Min Act: -0.0000

Data Index: 251771 (The Pile)

Max Activating Token Index: 774

Text #4

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1357526 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1019706 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1337779 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1155442 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1335618 (The Pile)

Max Activating Token Index: 508

Text #9

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4198. Min Act: -0.0000

Data Index: 581937 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1448944 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3545. Min Act: -0.0000

Data Index: 24922 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3996. Min Act: -0.0000

Data Index: 184434 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1867787 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4198. Min Act: -0.0000

Data Index: 907638 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1671613 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1592806 (The Pile)

Max Activating Token Index: 705

Text #17

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3921. Min Act: -0.0000

Data Index: 804738 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1710738 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3865. Min Act: -0.0000

Data Index: 400959 (The Pile)

Max Activating Token Index: 449