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

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

Neuron 3963 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: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1208471 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0603. Min Act: -0.0003

Data Index: 222246 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0568. Min Act: -0.0003

Data Index: 112334 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0566. Min Act: -0.0002

Data Index: 896049 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0552. Min Act: -0.0003

Data Index: 3820 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0504. Min Act: -0.0003

Data Index: 27181 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0504. Min Act: -0.0002

Data Index: 175334 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0505. Min Act: -0.0003

Data Index: 847083 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1091290 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0504. Min Act: -0.0003

Data Index: 757582 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0488. Min Act: -0.0003

Data Index: 157933 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0511. Min Act: -0.0002

Data Index: 396781 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1279725 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0485. Min Act: -0.0003

Data Index: 855105 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1355832 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0475. Min Act: -0.0003

Data Index: 696308 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0457. Min Act: -0.0003

Data Index: 571937 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0474. Min Act: -0.0003

Data Index: 784740 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1314725 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0455. Min Act: -0.0003

Data Index: 829000 (C4 (Web Text))

Max Activating Token Index: 320