Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1791 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1361. Min Range: -1.1361

Max Act: 1.1361. Min Act: -0.0000

Data Index: 595057 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.9261. Min Act: -0.0000

Data Index: 353893 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8508. Min Act: -0.0000

Data Index: 294329 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8253. Min Act: -0.0000

Data Index: 304700 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8176. Min Act: -0.0001

Data Index: 347521 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1086159 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8101. Min Act: -0.0001

Data Index: 1357786 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1326069 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7737. Min Act: -0.0000

Data Index: 844492 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8461. Min Act: -0.0001

Data Index: 443883 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7626. Min Act: -0.0001

Data Index: 502461 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7370. Min Act: -0.0001

Data Index: 731089 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8251. Min Act: -0.0000

Data Index: 652541 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7790. Min Act: -0.0000

Data Index: 542284 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7233. Min Act: -0.0000

Data Index: 266655 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1357230 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7567. Min Act: -0.0000

Data Index: 339059 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7426. Min Act: -0.0000

Data Index: 672260 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1309549 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7550. Min Act: -0.0000

Data Index: 449783 (C4 (Web Text))

Max Activating Token Index: 775