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

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

Neuron 3084 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1512935 (Python Code)

Max Activating Token Index: 298

Text #1

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.4427. Min Act: -0.0000

Data Index: 648949 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.4132. Min Act: -0.0000

Data Index: 998279 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.3721. Min Act: -0.0000

Data Index: 276599 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1070765 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1593778 (Python Code)

Max Activating Token Index: 309

Text #6

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2914. Min Act: -0.0000

Data Index: 502586 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1549207 (Python Code)

Max Activating Token Index: 597

Text #8

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.3101. Min Act: -0.0000

Data Index: 533925 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1244630 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2162. Min Act: -0.0000

Data Index: 190407 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2465. Min Act: -0.0000

Data Index: 81405 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1322110 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2311. Min Act: -0.0000

Data Index: 133063 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1642104 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2129. Min Act: -0.0000

Data Index: 159593 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1091344 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1264584 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1351487 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.6381. Min Range: -0.6381

Max Act: 0.2329. Min Act: -0.0000

Data Index: 87267 (C4 (Web Text))

Max Activating Token Index: 5