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

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

Neuron 3261 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: 4.2792. Min Range: -4.2792

Max Act: 4.2792. Min Act: -0.0000

Data Index: 1636317 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 4.2792. Min Range: -4.2792

Max Act: 4.2766. Min Act: -0.0000

Data Index: 1433599 (Python Code)

Max Activating Token Index: 229

Text #2

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.5914. Min Act: -0.0000

Data Index: 1475137 (Python Code)

Max Activating Token Index: 328

Text #3

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.7318. Min Act: -0.0000

Data Index: 1630023 (Python Code)

Max Activating Token Index: 356

Text #4

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.9274. Min Act: -0.0000

Data Index: 1444904 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.7534. Min Act: -0.0000

Data Index: 1374979 (Python Code)

Max Activating Token Index: 325

Text #6

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.7115. Min Act: -0.0000

Data Index: 1599923 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.8750. Min Act: -0.0000

Data Index: 1516577 (Python Code)

Max Activating Token Index: 872

Text #8

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.6406. Min Act: -0.0000

Data Index: 1370576 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.6451. Min Act: -0.0000

Data Index: 1482146 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.7553. Min Act: -0.0000

Data Index: 1443417 (Python Code)

Max Activating Token Index: 594

Text #11

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.5734. Min Act: -0.0000

Data Index: 1415512 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.7056. Min Act: -0.0000

Data Index: 1579345 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.6859. Min Act: -0.0000

Data Index: 1535480 (Python Code)

Max Activating Token Index: 1013

Text #14

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.6312. Min Act: -0.0000

Data Index: 1571529 (Python Code)

Max Activating Token Index: 691

Text #15

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.3437. Min Act: -0.0000

Data Index: 1533172 (Python Code)

Max Activating Token Index: 206

Text #16

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.5168. Min Act: -0.0000

Data Index: 1464202 (Python Code)

Max Activating Token Index: 600

Text #17

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.1563. Min Act: -0.0000

Data Index: 1393614 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.2759. Min Act: -0.0000

Data Index: 1442885 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 4.2792. Min Range: -4.2792

Max Act: 3.2340. Min Act: -0.0000

Data Index: 1390811 (Python Code)

Max Activating Token Index: 348