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

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

Neuron 1382 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6555. Min Act: -0.0001

Data Index: 362770 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6768. Min Act: -0.0001

Data Index: 785888 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6538. Min Act: -0.0001

Data Index: 1315412 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6608. Min Act: -0.0001

Data Index: 631422 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6270. Min Act: -0.0001

Data Index: 235401 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6461. Min Act: -0.0001

Data Index: 1293453 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6279. Min Act: -0.0001

Data Index: 235464 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6473. Min Act: -0.0001

Data Index: 373458 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5107. Min Act: -0.0001

Data Index: 811977 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5666. Min Act: -0.0001

Data Index: 421128 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5459. Min Act: -0.0001

Data Index: 771950 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5249. Min Act: -0.0001

Data Index: 299839 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5430. Min Act: -0.0001

Data Index: 552965 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5381. Min Act: -0.0001

Data Index: 1265435 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4979. Min Act: -0.0001

Data Index: 50389 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5167. Min Act: -0.0001

Data Index: 1105998 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5008. Min Act: -0.0001

Data Index: 392702 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5017. Min Act: -0.0001

Data Index: 1120598 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4607. Min Act: -0.0001

Data Index: 157150 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4703. Min Act: -0.0001

Data Index: 246887 (C4 (Web Text))

Max Activating Token Index: 946