Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1580 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6739. Min Act: -0.0000

Data Index: 570050 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5675. Min Act: -0.0000

Data Index: 648530 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5640. Min Act: -0.0000

Data Index: 549246 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5641. Min Act: -0.0000

Data Index: 947949 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5420. Min Act: -0.0000

Data Index: 113916 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4653. Min Act: -0.0000

Data Index: 933328 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4934. Min Act: -0.0000

Data Index: 861212 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5407. Min Act: -0.0000

Data Index: 635369 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1031962 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4714. Min Act: -0.0000

Data Index: 491136 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1120140 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4571. Min Act: -0.0000

Data Index: 191240 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4354. Min Act: -0.0000

Data Index: 884440 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4325. Min Act: -0.0000

Data Index: 32596 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4721. Min Act: -0.0000

Data Index: 169809 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4283. Min Act: -0.0000

Data Index: 921578 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4115. Min Act: -0.0000

Data Index: 914792 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4408. Min Act: -0.0000

Data Index: 844543 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4246. Min Act: -0.0000

Data Index: 986164 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4272. Min Act: -0.0000

Data Index: 300151 (C4 (Web Text))

Max Activating Token Index: 842