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

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

Neuron 1262 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.3394. Min Act: -0.0000

Data Index: 670552 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1106534 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2737. Min Act: -0.0000

Data Index: 951162 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2785. Min Act: -0.0000

Data Index: 305326 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2842. Min Act: -0.0000

Data Index: 473665 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2914. Min Act: -0.0000

Data Index: 769440 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2699. Min Act: -0.0000

Data Index: 605237 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2786. Min Act: -0.0000

Data Index: 761915 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2689. Min Act: -0.0000

Data Index: 432167 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2466. Min Act: -0.0000

Data Index: 749542 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1232904 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2680. Min Act: -0.0000

Data Index: 487058 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2605. Min Act: -0.0000

Data Index: 679453 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2432. Min Act: -0.0000

Data Index: 841900 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2366. Min Act: -0.0000

Data Index: 14313 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1139087 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2443. Min Act: -0.0000

Data Index: 442527 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1198431 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2233. Min Act: -0.0000

Data Index: 247426 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2277. Min Act: -0.0000

Data Index: 982291 (C4 (Web Text))

Max Activating Token Index: 725