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

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

Neuron 2876 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1580285 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1522683 (Python Code)

Max Activating Token Index: 278

Text #2

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1630414 (Python Code)

Max Activating Token Index: 877

Text #3

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1462983 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3589. Min Act: -0.0001

Data Index: 1465307 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1495304 (Python Code)

Max Activating Token Index: 555

Text #6

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1523078 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1499248 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1443008 (Python Code)

Max Activating Token Index: 87

Text #9

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1613663 (Python Code)

Max Activating Token Index: 922

Text #10

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1564348 (Python Code)

Max Activating Token Index: 564

Text #11

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1399222 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1631479 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1432946 (Python Code)

Max Activating Token Index: 741

Text #14

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1624230 (Python Code)

Max Activating Token Index: 627

Text #15

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2858. Min Act: -0.0000

Data Index: 585580 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1545366 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1645391 (Python Code)

Max Activating Token Index: 286

Text #18

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2850. Min Act: -0.0001

Data Index: 1489416 (Python Code)

Max Activating Token Index: 119

Text #19

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1508853 (Python Code)

Max Activating Token Index: 820