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

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

Neuron 698 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4759. Min Act: -0.0001

Data Index: 1142453 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4631. Min Act: -0.0001

Data Index: 980699 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4516. Min Act: -0.0001

Data Index: 445857 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4467. Min Act: -0.0001

Data Index: 269193 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4570. Min Act: -0.0002

Data Index: 949476 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4426. Min Act: -0.0001

Data Index: 798846 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4405. Min Act: -0.0001

Data Index: 732197 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4436. Min Act: -0.0001

Data Index: 567427 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4378. Min Act: -0.0001

Data Index: 772292 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4401. Min Act: -0.0001

Data Index: 895202 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4376. Min Act: -0.0001

Data Index: 568087 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4283. Min Act: -0.0002

Data Index: 907825 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4045. Min Act: -0.0001

Data Index: 1166793 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3929. Min Act: -0.0001

Data Index: 538961 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3873. Min Act: -0.0001

Data Index: 209944 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3855. Min Act: -0.0001

Data Index: 421544 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3776. Min Act: -0.0001

Data Index: 1356207 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3741. Min Act: -0.0001

Data Index: 823908 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3735. Min Act: -0.0001

Data Index: 946012 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3734. Min Act: -0.0001

Data Index: 565889 (C4 (Web Text))

Max Activating Token Index: 902