Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 656 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.7515. Min Act: -0.0000

Data Index: 813882 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.7444. Min Act: -0.0000

Data Index: 155789 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.7127. Min Act: -0.0000

Data Index: 861478 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6936. Min Act: -0.0001

Data Index: 349072 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.7108. Min Act: -0.0001

Data Index: 71507 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6643. Min Act: -0.0000

Data Index: 872569 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6432. Min Act: -0.0000

Data Index: 949314 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6805. Min Act: -0.0000

Data Index: 896685 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6598. Min Act: -0.0001

Data Index: 931713 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1102348 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6527. Min Act: -0.0000

Data Index: 742127 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1082860 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6428. Min Act: -0.0000

Data Index: 553978 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6415. Min Act: -0.0000

Data Index: 650148 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6095. Min Act: -0.0001

Data Index: 802721 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6280. Min Act: -0.0001

Data Index: 580267 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6229. Min Act: -0.0001

Data Index: 93001 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6160. Min Act: -0.0000

Data Index: 688698 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1251883 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6083. Min Act: -0.0001

Data Index: 921555 (C4 (Web Text))

Max Activating Token Index: 791