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

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

Neuron 306 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0001

Data Index: 789980 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0511. Min Act: -0.0001

Data Index: 560967 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0510. Min Act: -0.0001

Data Index: 264361 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0498. Min Act: -0.0001

Data Index: 962123 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0490. Min Act: -0.0001

Data Index: 96180 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0483. Min Act: -0.0001

Data Index: 528232 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1317710 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0477. Min Act: -0.0001

Data Index: 737713 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0414. Min Act: -0.0001

Data Index: 449838 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0447. Min Act: -0.0001

Data Index: 569685 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0414. Min Act: -0.0001

Data Index: 269054 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1279924 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0471. Min Act: -0.0001

Data Index: 532755 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0433. Min Act: -0.0001

Data Index: 706561 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0411. Min Act: -0.0001

Data Index: 744678 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0415. Min Act: -0.0001

Data Index: 376651 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0435. Min Act: -0.0001

Data Index: 238707 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1358255 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0429. Min Act: -0.0001

Data Index: 30920 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1169577 (C4 (Web Text))

Max Activating Token Index: 666