Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3499 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.7253. Min Act: 0.0001

Data Index: 1269148 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.6874. Min Act: -0.0000

Data Index: 1215741 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.4417. Min Act: -0.0000

Data Index: 343666 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.4367. Min Act: 0.0005

Data Index: 102647 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.3765. Min Act: -0.0000

Data Index: 457387 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.3705. Min Act: -0.0000

Data Index: 278709 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.4220. Min Act: -0.0000

Data Index: 812613 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.3514. Min Act: -0.0000

Data Index: 158809 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2464. Min Act: -0.0000

Data Index: 425788 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.3101. Min Act: 0.0002

Data Index: 790114 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2139. Min Act: -0.0000

Data Index: 252426 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2891. Min Act: -0.0000

Data Index: 743288 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1359445 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.3291. Min Act: -0.0000

Data Index: 1517276 (Python Code)

Max Activating Token Index: 881

Text #14

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1466. Min Act: -0.0000

Data Index: 467466 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1508. Min Act: -0.0000

Data Index: 209571 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1156676 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1933. Min Act: -0.0000

Data Index: 618111 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2017. Min Act: -0.0000

Data Index: 173205 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2172. Min Act: -0.0000

Data Index: 804208 (C4 (Web Text))

Max Activating Token Index: 284