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

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

Neuron 2825 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.8449. Min Act: -0.0000

Data Index: 163166 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.7450. Min Act: -0.0000

Data Index: 261940 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.4692. Min Act: -0.0000

Data Index: 982363 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.2528. Min Act: -0.0000

Data Index: 380450 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.2455. Min Act: -0.0000

Data Index: 853452 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.3810. Min Act: -0.0000

Data Index: 536686 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.1931. Min Act: -0.0000

Data Index: 958657 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.0799. Min Act: -0.0000

Data Index: 161506 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1002163 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.0818. Min Act: -0.0000

Data Index: 284763 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.0825. Min Act: -0.0000

Data Index: 491813 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1077268 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1336596 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9938. Min Act: -0.0000

Data Index: 986328 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9689. Min Act: -0.0000

Data Index: 48538 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9578. Min Act: -0.0000

Data Index: 1319365 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9424. Min Act: -0.0000

Data Index: 890646 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1071512 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9353. Min Act: -0.0000

Data Index: 955233 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9351. Min Act: -0.0000

Data Index: 182404 (C4 (Web Text))

Max Activating Token Index: 620