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

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

Neuron 4378 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0002

Data Index: 541606 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0509. Min Act: -0.0002

Data Index: 137023 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0507. Min Act: -0.0002

Data Index: 521698 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0469. Min Act: -0.0001

Data Index: 590153 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0487. Min Act: -0.0001

Data Index: 86086 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0452. Min Act: -0.0002

Data Index: 751785 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0471. Min Act: -0.0002

Data Index: 225575 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0469. Min Act: -0.0002

Data Index: 818541 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0447. Min Act: -0.0002

Data Index: 486375 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1223150 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0461. Min Act: -0.0002

Data Index: 415501 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1149024 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0456. Min Act: -0.0002

Data Index: 849684 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0426. Min Act: -0.0001

Data Index: 219413 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0432. Min Act: -0.0002

Data Index: 164293 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0420. Min Act: -0.0002

Data Index: 761762 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0455. Min Act: -0.0002

Data Index: 34481 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1042012 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0413. Min Act: -0.0002

Data Index: 643926 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0377. Min Act: -0.0002

Data Index: 220166 (C4 (Web Text))

Max Activating Token Index: 705