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

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

Neuron 3627 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.7631. Min Act: -0.0000

Data Index: 410048 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.7011. Min Act: -0.0000

Data Index: 1070582 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.5562. Min Act: -0.0000

Data Index: 41359 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.5403. Min Act: -0.0000

Data Index: 1128011 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.5644. Min Act: -0.0000

Data Index: 617295 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.5383. Min Act: -0.0000

Data Index: 1301781 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.1335. Min Act: -0.0000

Data Index: 917402 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.3335. Min Act: -0.0000

Data Index: 413091 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.4420. Min Act: -0.0000

Data Index: 255928 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.3417. Min Act: -0.0000

Data Index: 918958 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.2174. Min Act: -0.0000

Data Index: 326196 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.3234. Min Act: -0.0000

Data Index: 10724 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.2911. Min Act: -0.0000

Data Index: 447385 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.2847. Min Act: -0.0000

Data Index: 881393 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.3894. Min Act: -0.0000

Data Index: 688840 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.2637. Min Act: -0.0000

Data Index: 380630 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 2.7631. Min Range: -2.7631

Max Act: 1.9103. Min Act: -0.0000

Data Index: 788911 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.2450. Min Act: -0.0000

Data Index: 1152772 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.3285. Min Act: -0.0000

Data Index: 796116 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 2.7631. Min Range: -2.7631

Max Act: 2.2004. Min Act: -0.0000

Data Index: 504867 (C4 (Web Text))

Max Activating Token Index: 424