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

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

Neuron 1435 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2846. Min Range: -3.2846

Max Act: 3.2846. Min Act: -0.0000

Data Index: 1013264 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 3.2846. Min Range: -3.2846

Max Act: 3.1028. Min Act: -0.0000

Data Index: 54174 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.9779. Min Act: -0.0000

Data Index: 51595 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.9406. Min Act: -0.0000

Data Index: 577108 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.8399. Min Act: -0.0000

Data Index: 541195 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.1945. Min Act: -0.0000

Data Index: 643844 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.2714. Min Act: -0.0000

Data Index: 1285382 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.2519. Min Act: -0.0000

Data Index: 868964 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.3467. Min Act: -0.0000

Data Index: 371920 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.2155. Min Act: -0.0000

Data Index: 987618 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 3.2846. Min Range: -3.2846

Max Act: 1.9792. Min Act: -0.0000

Data Index: 900656 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.2057. Min Act: -0.0000

Data Index: 845935 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.0662. Min Act: -0.0000

Data Index: 1173152 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 3.2846. Min Range: -3.2846

Max Act: 1.9541. Min Act: -0.0000

Data Index: 610432 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 3.2846. Min Range: -3.2846

Max Act: 2.0648. Min Act: -0.0000

Data Index: 995765 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 3.2846. Min Range: -3.2846

Max Act: 1.8025. Min Act: -0.0000

Data Index: 647233 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 3.2846. Min Range: -3.2846

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1014494 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 3.2846. Min Range: -3.2846

Max Act: 1.9978. Min Act: -0.0000

Data Index: 1300234 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 3.2846. Min Range: -3.2846

Max Act: 1.8218. Min Act: -0.0000

Data Index: 957009 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 3.2846. Min Range: -3.2846

Max Act: 1.8065. Min Act: -0.0000

Data Index: 975116 (C4 (Web Text))

Max Activating Token Index: 579