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

Dataset: The Pile

Neuron 3344 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: 8.4871. Min Range: -8.4871

Max Act: 8.4871. Min Act: -0.0000

Data Index: 1001060 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.7249. Min Act: -0.0000

Data Index: 55931 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 8.4871. Min Range: -8.4871

Max Act: 8.0487. Min Act: -0.0000

Data Index: 903125 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.8093. Min Act: -0.0000

Data Index: 1135840 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.5188. Min Act: -0.0000

Data Index: 826110 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.4796. Min Act: -0.0000

Data Index: 114644 (The Pile)

Max Activating Token Index: 174

Text #6

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.0703. Min Act: -0.0000

Data Index: 1322690 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.4058. Min Act: -0.0000

Data Index: 1598255 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 8.4871. Min Range: -8.4871

Max Act: 8.0260. Min Act: -0.0000

Data Index: 1385574 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.6525. Min Act: -0.0000

Data Index: 1885216 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.1311. Min Act: -0.0000

Data Index: 1086005 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.4885. Min Act: -0.0000

Data Index: 1532159 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.6027. Min Act: -0.0000

Data Index: 1446880 (The Pile)

Max Activating Token Index: 52

Text #13

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.6035. Min Act: -0.0000

Data Index: 335607 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.4182. Min Act: -0.0000

Data Index: 1484950 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.1776. Min Act: -0.0000

Data Index: 286060 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.1422. Min Act: -0.0000

Data Index: 1744854 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 8.4871. Min Range: -8.4871

Max Act: 6.7479. Min Act: -0.0000

Data Index: 1811340 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 8.4871. Min Range: -8.4871

Max Act: 7.2665. Min Act: -0.0000

Data Index: 1666089 (The Pile)

Max Activating Token Index: 28

Text #19

Max Range: 8.4871. Min Range: -8.4871

Max Act: 6.6756. Min Act: -0.0000

Data Index: 12640 (The Pile)

Max Activating Token Index: 673