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

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

Neuron 4769 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.4034. Min Act: -0.0000

Data Index: 369901 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3228. Min Act: -0.0001

Data Index: 1333075 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.1299. Min Act: -0.0001

Data Index: 895959 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3728. Min Act: -0.0001

Data Index: 1247603 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3557. Min Act: -0.0001

Data Index: 543553 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3639. Min Act: -0.0001

Data Index: 331895 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3180. Min Act: -0.0000

Data Index: 263394 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.4042. Min Act: -0.0001

Data Index: 388850 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2563. Min Act: -0.0001

Data Index: 1138851 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2578. Min Act: -0.0001

Data Index: 798468 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2844. Min Act: -0.0001

Data Index: 951700 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3691. Min Act: -0.0001

Data Index: 7885 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.4017. Min Act: -0.0001

Data Index: 70763 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.4318. Min Act: -0.0001

Data Index: 785806 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2652. Min Act: -0.0000

Data Index: 965989 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2515. Min Act: -0.0000

Data Index: 261079 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2427. Min Act: -0.0001

Data Index: 71007 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2196. Min Act: -0.0001

Data Index: 786571 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1318509 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2792. Min Act: -0.0001

Data Index: 250374 (C4 (Web Text))

Max Activating Token Index: 802