Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1685 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0530. Min Act: -0.0004

Data Index: 1223467 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0495. Min Act: -0.0004

Data Index: 39866 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1345225 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0462. Min Act: -0.0002

Data Index: 588604 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0455. Min Act: -0.0003

Data Index: 762273 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0452. Min Act: -0.0002

Data Index: 44147 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0434. Min Act: -0.0003

Data Index: 690557 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0424. Min Act: -0.0003

Data Index: 926759 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1081000 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0420. Min Act: -0.0002

Data Index: 2679 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1242410 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1276544 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0400. Min Act: -0.0003

Data Index: 981012 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0398. Min Act: -0.0003

Data Index: 950905 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0398. Min Act: -0.0002

Data Index: 687134 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0384. Min Act: -0.0003

Data Index: 536080 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1162800 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0391. Min Act: -0.0003

Data Index: 393009 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0385. Min Act: -0.0002

Data Index: 905909 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1326408 (C4 (Web Text))

Max Activating Token Index: 766