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

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

Neuron 670 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.7362. Min Act: -0.0000

Data Index: 386687 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.3578. Min Act: -0.0000

Data Index: 1067236 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.4323. Min Act: -0.0000

Data Index: 762569 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.2608. Min Act: -0.0000

Data Index: 341676 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.1271. Min Act: -0.0000

Data Index: 180794 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.2462. Min Act: -0.0000

Data Index: 465535 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0875. Min Act: -0.0000

Data Index: 304904 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.2391. Min Act: -0.0000

Data Index: 588476 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.1053. Min Act: -0.0000

Data Index: 964078 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9576. Min Act: -0.0000

Data Index: 1236287 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0585. Min Act: -0.0000

Data Index: 1117633 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.0598. Min Act: -0.0000

Data Index: 1126715 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9407. Min Act: -0.0000

Data Index: 402921 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 2.7362. Min Range: -2.7362

Max Act: 2.1280. Min Act: -0.0000

Data Index: 594074 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9953. Min Act: -0.0000

Data Index: 1051134 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9833. Min Act: -0.0000

Data Index: 1065139 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9940. Min Act: -0.0000

Data Index: 1062870 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9866. Min Act: -0.0000

Data Index: 133173 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9748. Min Act: -0.0000

Data Index: 632956 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 2.7362. Min Range: -2.7362

Max Act: 1.9763. Min Act: -0.0001

Data Index: 1234605 (C4 (Web Text))

Max Activating Token Index: 933