Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1450 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.8684. Min Act: -0.0001

Data Index: 172427 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.8349. Min Act: -0.0001

Data Index: 50352 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.8474. Min Act: -0.0001

Data Index: 396352 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.7661. Min Act: -0.0001

Data Index: 1201186 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.5788. Min Act: -0.0001

Data Index: 770628 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.5275. Min Act: -0.0001

Data Index: 1049187 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.6511. Min Act: -0.0001

Data Index: 1091803 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.5560. Min Act: -0.0001

Data Index: 867919 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.5034. Min Act: -0.0001

Data Index: 825696 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.5788. Min Act: -0.0001

Data Index: 233636 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.5937. Min Act: -0.0001

Data Index: 15262 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.5217. Min Act: -0.0001

Data Index: 1303030 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.3488. Min Act: -0.0001

Data Index: 123871 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.3803. Min Act: -0.0001

Data Index: 1151880 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.4186. Min Act: -0.0001

Data Index: 961271 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.4495. Min Act: -0.0001

Data Index: 256802 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.4450. Min Act: -0.0001

Data Index: 270854 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.4409. Min Act: -0.0001

Data Index: 1061751 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.4244. Min Act: -0.0001

Data Index: 676367 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 1.8684. Min Range: -1.8684

Max Act: 1.3370. Min Act: -0.0001

Data Index: 1319645 (C4 (Web Text))

Max Activating Token Index: 210