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

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

Neuron 1714 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.7894. Min Act: -0.0001

Data Index: 1427351 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.8082. Min Act: -0.0001

Data Index: 68703 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.6550. Min Act: -0.0001

Data Index: 630106 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.6495. Min Act: -0.0001

Data Index: 1477443 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.6024. Min Act: -0.0001

Data Index: 1208239 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5777. Min Act: -0.0001

Data Index: 1618666 (Python Code)

Max Activating Token Index: 481

Text #6

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.6517. Min Act: -0.0001

Data Index: 546379 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5620. Min Act: -0.0001

Data Index: 669993 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5771. Min Act: -0.0001

Data Index: 894776 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5982. Min Act: -0.0001

Data Index: 819039 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5322. Min Act: -0.0001

Data Index: 309334 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5364. Min Act: -0.0001

Data Index: 166082 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5381. Min Act: -0.0001

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5721. Min Act: -0.0001

Data Index: 848183 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5305. Min Act: -0.0001

Data Index: 75723 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5371. Min Act: -0.0001

Data Index: 23204 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5333. Min Act: -0.0001

Data Index: 521566 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5515. Min Act: -0.0001

Data Index: 315956 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5142. Min Act: -0.0001

Data Index: 628184 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5513. Min Act: -0.0001

Data Index: 665123 (C4 (Web Text))

Max Activating Token Index: 383