Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 784 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.7482. Min Act: -0.0002

Data Index: 354858 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6594. Min Act: -0.0001

Data Index: 1186925 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6657. Min Act: -0.0001

Data Index: 1395532 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6628. Min Act: -0.0002

Data Index: 1175159 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6611. Min Act: -0.0002

Data Index: 1093431 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6538. Min Act: -0.0002

Data Index: 307471 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6705. Min Act: -0.0001

Data Index: 1542019 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6302. Min Act: -0.0001

Data Index: 1634989 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6065. Min Act: -0.0002

Data Index: 744279 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6306. Min Act: -0.0002

Data Index: 447048 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6062. Min Act: -0.0002

Data Index: 914982 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6971. Min Act: -0.0002

Data Index: 1069407 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6209. Min Act: -0.0001

Data Index: 1241998 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.5808. Min Act: -0.0002

Data Index: 164389 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6355. Min Act: -0.0002

Data Index: 1358551 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6311. Min Act: -0.0002

Data Index: 1002921 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.5996. Min Act: -0.0002

Data Index: 1302811 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6352. Min Act: -0.0001

Data Index: 60673 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.5671. Min Act: -0.0002

Data Index: 1355654 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6577. Min Act: -0.0002

Data Index: 618149 (C4 (Web Text))

Max Activating Token Index: 733