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

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

Neuron 2159 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: 0.7839. Min Range: -0.7839

Max Act: 0.7839. Min Act: -0.0000

Data Index: 318555 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.6628. Min Act: -0.0000

Data Index: 540998 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.6415. Min Act: -0.0000

Data Index: 810557 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1429069 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5964. Min Act: -0.0000

Data Index: 304882 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1633329 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.6105. Min Act: -0.0000

Data Index: 738644 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1286019 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5752. Min Act: -0.0000

Data Index: 561198 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5589. Min Act: -0.0000

Data Index: 171929 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1284107 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5662. Min Act: -0.0000

Data Index: 790364 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1380978 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1630752 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5280. Min Act: -0.0000

Data Index: 976061 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1459013 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5471. Min Act: -0.0000

Data Index: 224276 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1454911 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1149169 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.7839. Min Range: -0.7839

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1389244 (Python Code)

Max Activating Token Index: 779