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

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

Neuron 3196 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.4395. Min Act: -0.0001

Data Index: 1053514 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3381. Min Act: -0.0001

Data Index: 870265 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.2036. Min Act: -0.0001

Data Index: 173998 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.2358. Min Act: -0.0001

Data Index: 529492 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.2256. Min Act: -0.0001

Data Index: 547896 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.1581. Min Act: -0.0001

Data Index: 1138945 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.1397. Min Act: -0.0001

Data Index: 576951 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0943. Min Act: -0.0001

Data Index: 536073 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0544. Min Act: -0.0001

Data Index: 1052484 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.9936. Min Act: -0.0001

Data Index: 1114951 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.1078. Min Act: -0.0000

Data Index: 766097 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0878. Min Act: -0.0001

Data Index: 85819 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.1131. Min Act: -0.0001

Data Index: 1342835 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0443. Min Act: -0.0001

Data Index: 812962 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0438. Min Act: -0.0001

Data Index: 1152504 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0619. Min Act: -0.0001

Data Index: 528161 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0027. Min Act: -0.0001

Data Index: 1354630 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0001. Min Act: -0.0001

Data Index: 366282 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0146. Min Act: -0.0001

Data Index: 302671 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.9910. Min Act: -0.0000

Data Index: 104890 (C4 (Web Text))

Max Activating Token Index: 36