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

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

Neuron 3756 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.9366. Min Act: -0.0001

Data Index: 369956 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.9525. Min Act: -0.0001

Data Index: 1055620 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.9104. Min Act: -0.0001

Data Index: 288152 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.7635. Min Act: -0.0001

Data Index: 726698 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.7277. Min Act: -0.0001

Data Index: 1358407 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.6424. Min Act: -0.0001

Data Index: 1185388 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.4013. Min Act: -0.0001

Data Index: 78352 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.6810. Min Act: -0.0001

Data Index: 392763 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.5158. Min Act: -0.0001

Data Index: 443114 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.6377. Min Act: -0.0001

Data Index: 499530 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.4545. Min Act: -0.0001

Data Index: 1342158 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.5658. Min Act: -0.0001

Data Index: 434656 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.5152. Min Act: -0.0001

Data Index: 1118900 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.5234. Min Act: -0.0001

Data Index: 545769 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.5485. Min Act: -0.0001

Data Index: 27623 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.4568. Min Act: -0.0001

Data Index: 141685 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.4827. Min Act: -0.0001

Data Index: 684385 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.6429. Min Act: -0.0001

Data Index: 103389 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.5033. Min Act: -0.0001

Data Index: 1145929 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 1.9525. Min Range: -1.9525

Max Act: 1.5312. Min Act: -0.0001

Data Index: 289522 (C4 (Web Text))

Max Activating Token Index: 388