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

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

Neuron 2084 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.3209. Min Act: -0.0001

Data Index: 1276702 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.2709. Min Act: -0.0001

Data Index: 1244691 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.3155. Min Act: -0.0001

Data Index: 429178 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.2390. Min Act: -0.0001

Data Index: 1142687 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.3251. Min Act: -0.0001

Data Index: 1032716 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.2401. Min Act: -0.0001

Data Index: 535868 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1008. Min Act: -0.0001

Data Index: 498373 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9685. Min Act: -0.0001

Data Index: 988470 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0947. Min Act: -0.0001

Data Index: 625503 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1467. Min Act: -0.0001

Data Index: 681799 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1377. Min Act: -0.0001

Data Index: 792682 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0944. Min Act: -0.0001

Data Index: 1108427 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0347. Min Act: -0.0001

Data Index: 922953 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0722. Min Act: -0.0001

Data Index: 899547 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0735. Min Act: -0.0001

Data Index: 41320 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1054. Min Act: -0.0001

Data Index: 945468 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9741. Min Act: -0.0001

Data Index: 368067 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0580. Min Act: -0.0001

Data Index: 524578 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9459. Min Act: -0.0001

Data Index: 418527 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0285. Min Act: -0.0001

Data Index: 502961 (C4 (Web Text))

Max Activating Token Index: 560