Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 163 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0487. Min Act: -0.0006

Data Index: 1221112 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0466. Min Act: -0.0006

Data Index: 937170 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0494. Min Act: -0.0006

Data Index: 852184 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0462. Min Act: -0.0006

Data Index: 826579 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0458. Min Act: -0.0006

Data Index: 443170 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0449. Min Act: -0.0006

Data Index: 1280637 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0438. Min Act: -0.0006

Data Index: 659649 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0454. Min Act: -0.0006

Data Index: 1242453 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0453. Min Act: -0.0006

Data Index: 1014358 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0434. Min Act: -0.0006

Data Index: 1231410 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0442. Min Act: -0.0006

Data Index: 671704 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0468. Min Act: -0.0006

Data Index: 162088 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0445. Min Act: -0.0006

Data Index: 764404 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0444. Min Act: -0.0006

Data Index: 493011 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0444. Min Act: -0.0006

Data Index: 206417 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0445. Min Act: -0.0006

Data Index: 608195 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0440. Min Act: -0.0006

Data Index: 465451 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0450. Min Act: -0.0006

Data Index: 668508 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0433. Min Act: -0.0006

Data Index: 408967 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0440. Min Act: -0.0006

Data Index: 46377 (C4 (Web Text))

Max Activating Token Index: 677