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

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

Neuron 524 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: 0.4065. Min Range: -0.4065

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1436104 (Python Code)

Max Activating Token Index: 861

Text #1

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1459438 (Python Code)

Max Activating Token Index: 859

Text #2

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1365556 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1459969 (Python Code)

Max Activating Token Index: 260

Text #4

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1501964 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1501211 (Python Code)

Max Activating Token Index: 207

Text #6

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1413389 (Python Code)

Max Activating Token Index: 242

Text #7

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1501997 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1383715 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1468975 (Python Code)

Max Activating Token Index: 179

Text #10

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1582016 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1569526 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1482250 (Python Code)

Max Activating Token Index: 102

Text #13

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1572047 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1490200 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1523460 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1578312 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1605321 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1514509 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1653420 (Python Code)

Max Activating Token Index: 42