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

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

Neuron 4545 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0003

Data Index: 601391 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0477. Min Act: -0.0003

Data Index: 59418 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0489. Min Act: -0.0002

Data Index: 752163 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0488. Min Act: -0.0003

Data Index: 814447 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1292162 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0471. Min Act: -0.0003

Data Index: 298916 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0466. Min Act: -0.0003

Data Index: 424233 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0476. Min Act: -0.0002

Data Index: 5813 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1304904 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0459. Min Act: -0.0003

Data Index: 849411 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0472. Min Act: -0.0003

Data Index: 494770 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0447. Min Act: -0.0002

Data Index: 497536 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0450. Min Act: -0.0003

Data Index: 68520 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0450. Min Act: -0.0003

Data Index: 311315 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0443. Min Act: -0.0003

Data Index: 873669 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0434. Min Act: -0.0003

Data Index: 718836 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0432. Min Act: -0.0003

Data Index: 340028 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0442. Min Act: -0.0003

Data Index: 132263 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0423. Min Act: -0.0003

Data Index: 125959 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0426. Min Act: -0.0002

Data Index: 755896 (C4 (Web Text))

Max Activating Token Index: 325