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

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

Neuron 4908 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1286325 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5488. Min Act: -0.0000

Data Index: 235821 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1020397 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5566. Min Act: -0.0000

Data Index: 573368 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5029. Min Act: -0.0000

Data Index: 425237 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4691. Min Act: -0.0000

Data Index: 760480 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1208118 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4338. Min Act: -0.0000

Data Index: 260449 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1600254 (Python Code)

Max Activating Token Index: 247

Text #9

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4316. Min Act: -0.0000

Data Index: 549605 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4185. Min Act: -0.0000

Data Index: 191167 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1300954 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1355750 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3868. Min Act: -0.0000

Data Index: 145523 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1488201 (Python Code)

Max Activating Token Index: 984

Text #15

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3669. Min Act: -0.0000

Data Index: 722350 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3780. Min Act: -0.0000

Data Index: 976468 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3893. Min Act: -0.0000

Data Index: 207142 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1037445 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3535. Min Act: -0.0000

Data Index: 228777 (C4 (Web Text))

Max Activating Token Index: 460