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

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

Neuron 4520 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: 2.2359. Min Range: -2.2359

Max Act: 2.2359. Min Act: -0.0000

Data Index: 289459 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.9273. Min Act: -0.0000

Data Index: 388721 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.6606. Min Act: -0.0000

Data Index: 591910 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.6759. Min Act: -0.0000

Data Index: 1251226 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.7425. Min Act: -0.0000

Data Index: 650026 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.6111. Min Act: -0.0000

Data Index: 420564 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.5191. Min Act: -0.0000

Data Index: 274686 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.6111. Min Act: -0.0000

Data Index: 993085 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.5854. Min Act: -0.0000

Data Index: 150591 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.5836. Min Act: -0.0000

Data Index: 458687 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.6717. Min Act: -0.0000

Data Index: 289445 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.6534. Min Act: -0.0001

Data Index: 1090262 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.4433. Min Act: -0.0000

Data Index: 640148 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.5218. Min Act: -0.0000

Data Index: 1185403 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.4292. Min Act: -0.0000

Data Index: 347102 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.3790. Min Act: -0.0000

Data Index: 1030369 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.4414. Min Act: -0.0000

Data Index: 819680 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.4405. Min Act: -0.0000

Data Index: 552523 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.4156. Min Act: -0.0000

Data Index: 683647 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 2.2359. Min Range: -2.2359

Max Act: 1.3979. Min Act: -0.0000

Data Index: 255216 (C4 (Web Text))

Max Activating Token Index: 492