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

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

Neuron 2744 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: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1026962 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0491. Min Act: -0.0001

Data Index: 85773 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0454. Min Act: -0.0001

Data Index: 271350 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1309601 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0451. Min Act: -0.0001

Data Index: 871796 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0439. Min Act: -0.0001

Data Index: 780374 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0444. Min Act: -0.0001

Data Index: 560229 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0416. Min Act: -0.0001

Data Index: 365670 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0402. Min Act: -0.0001

Data Index: 462745 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0438. Min Act: -0.0001

Data Index: 496739 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0406. Min Act: -0.0001

Data Index: 873609 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0400. Min Act: -0.0001

Data Index: 600337 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1423625 (Python Code)

Max Activating Token Index: 384

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0406. Min Act: -0.0001

Data Index: 772626 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0379. Min Act: -0.0001

Data Index: 222289 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1213752 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0421. Min Act: -0.0001

Data Index: 458518 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1163111 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1198803 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0389. Min Act: -0.0001

Data Index: 463470 (C4 (Web Text))

Max Activating Token Index: 844