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

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

Neuron 652 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: 0.3919. Min Range: -0.3919

Max Act: 0.3919. Min Act: -0.0001

Data Index: 1353126 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3684. Min Act: -0.0001

Data Index: 172892 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3658. Min Act: -0.0001

Data Index: 255603 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3385. Min Act: -0.0001

Data Index: 829267 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3432. Min Act: -0.0001

Data Index: 918876 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3559. Min Act: -0.0001

Data Index: 1272707 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3316. Min Act: -0.0001

Data Index: 188536 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1067580 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3065. Min Act: -0.0001

Data Index: 884419 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3199. Min Act: -0.0001

Data Index: 686884 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3285. Min Act: -0.0001

Data Index: 608397 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3359. Min Act: -0.0001

Data Index: 496567 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3260. Min Act: -0.0001

Data Index: 532396 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3398. Min Act: -0.0001

Data Index: 699268 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3250. Min Act: -0.0001

Data Index: 700208 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3355. Min Act: -0.0001

Data Index: 315407 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1299 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3229. Min Act: -0.0001

Data Index: 189218 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3332. Min Act: -0.0001

Data Index: 791534 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.3919. Min Range: -0.3919

Max Act: 0.3126. Min Act: -0.0001

Data Index: 167732 (C4 (Web Text))

Max Activating Token Index: 619