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

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

Neuron 2136 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9644. Min Act: -0.0000

Data Index: 92993 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.0287. Min Range: -1.0287

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1317874 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9926. Min Act: -0.0000

Data Index: 63082 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.0287. Min Range: -1.0287

Max Act: 1.0058. Min Act: -0.0000

Data Index: 816885 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9164. Min Act: -0.0000

Data Index: 732306 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 1.0287. Min Range: -1.0287

Max Act: 1.0287. Min Act: -0.0000

Data Index: 988924 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9573. Min Act: -0.0000

Data Index: 620607 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9520. Min Act: -0.0000

Data Index: 427753 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9938. Min Act: -0.0000

Data Index: 663982 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9089. Min Act: -0.0000

Data Index: 886433 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9591. Min Act: -0.0000

Data Index: 307835 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8989. Min Act: -0.0000

Data Index: 158995 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8932. Min Act: -0.0000

Data Index: 385665 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1104852 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9530. Min Act: -0.0000

Data Index: 801670 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9171. Min Act: -0.0000

Data Index: 503043 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8880. Min Act: -0.0000

Data Index: 516953 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8783. Min Act: -0.0000

Data Index: 655771 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9359. Min Act: -0.0000

Data Index: 692048 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8867. Min Act: -0.0000

Data Index: 995844 (C4 (Web Text))

Max Activating Token Index: 505