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

Dataset: The Pile

Neuron 1645 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.7020. Min Act: -0.0000

Data Index: 1930327 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.5705. Min Act: -0.0000

Data Index: 282536 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.5907. Min Act: -0.0000

Data Index: 345488 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.6159. Min Act: -0.0000

Data Index: 1847470 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.7769. Min Act: -0.0000

Data Index: 1745663 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.5698. Min Act: -0.0000

Data Index: 1962410 (The Pile)

Max Activating Token Index: 69

Text #6

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.7694. Min Act: -0.0000

Data Index: 910606 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.7380. Min Act: -0.0000

Data Index: 1711828 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.5127. Min Act: -0.0000

Data Index: 751257 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.5037. Min Act: -0.0000

Data Index: 339682 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.3915. Min Act: -0.0000

Data Index: 427252 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.5764. Min Act: -0.0000

Data Index: 880214 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.5438. Min Act: -0.0000

Data Index: 980153 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.5226. Min Act: -0.0000

Data Index: 1370389 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.4014. Min Act: -0.0000

Data Index: 584029 (The Pile)

Max Activating Token Index: 536

Text #15

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1238674 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.3392. Min Act: -0.0000

Data Index: 297494 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.4885. Min Act: -0.0000

Data Index: 1292823 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1030439 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 1.7769. Min Range: -1.7769

Max Act: 1.5483. Min Act: -0.0000

Data Index: 1565022 (The Pile)

Max Activating Token Index: 610