Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1489 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.5896. Min Act: -0.0000

Data Index: 405845 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3714. Min Act: -0.0000

Data Index: 1219104 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3719. Min Act: -0.0000

Data Index: 10650 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3071. Min Act: -0.0000

Data Index: 890055 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3134. Min Act: -0.0000

Data Index: 868782 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3012. Min Act: -0.0000

Data Index: 399008 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1330140 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2154. Min Act: -0.0000

Data Index: 537104 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2665. Min Act: -0.0000

Data Index: 992384 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2175. Min Act: -0.0000

Data Index: 621105 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2962. Min Act: -0.0000

Data Index: 313131 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3081. Min Act: -0.0000

Data Index: 616083 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.0963. Min Act: -0.0000

Data Index: 978209 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1352438 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2897. Min Act: -0.0000

Data Index: 302167 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.1628. Min Act: -0.0000

Data Index: 852536 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.1112. Min Act: -0.0000

Data Index: 685424 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1184290 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.1522. Min Act: -0.0000

Data Index: 423502 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.1028. Min Act: -0.0000

Data Index: 858130 (C4 (Web Text))

Max Activating Token Index: 742