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

Dataset: The Pile

Neuron 2245 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.5853. Min Act: -0.0000

Data Index: 1504971 (The Pile)

Max Activating Token Index: 253

Text #1

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2117. Min Act: -0.0000

Data Index: 945342 (The Pile)

Max Activating Token Index: 317

Text #2

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0690. Min Act: -0.0000

Data Index: 878514 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1422829 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.9903. Min Act: -0.0000

Data Index: 1857270 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1326454 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1636279 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1242136 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1148704 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.7155. Min Act: -0.0000

Data Index: 394407 (The Pile)

Max Activating Token Index: 208

Text #10

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.7197. Min Act: -0.0000

Data Index: 411143 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.6875. Min Act: -0.0000

Data Index: 319788 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.7734. Min Act: -0.0000

Data Index: 683684 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1382353 (The Pile)

Max Activating Token Index: 78

Text #14

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1421333 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.6824. Min Act: -0.0000

Data Index: 9630 (The Pile)

Max Activating Token Index: 840

Text #16

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1353409 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1198239 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1948144 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.5779. Min Act: -0.0000

Data Index: 964786 (The Pile)

Max Activating Token Index: 288