Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1407 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.8457. Min Act: -0.0000

Data Index: 1581595 (Python Code)

Max Activating Token Index: 316

Text #1

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.8952. Min Act: -0.0000

Data Index: 1376273 (Python Code)

Max Activating Token Index: 330

Text #2

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.6843. Min Act: -0.0000

Data Index: 1504047 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.9360. Min Act: -0.0000

Data Index: 1366122 (Python Code)

Max Activating Token Index: 245

Text #4

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.4186. Min Act: -0.0000

Data Index: 1536243 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 8.9360. Min Range: -8.9360

Max Act: 7.9536. Min Act: -0.0000

Data Index: 1372716 (Python Code)

Max Activating Token Index: 816

Text #6

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.0302. Min Act: -0.0000

Data Index: 1402373 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.2067. Min Act: -0.0000

Data Index: 1532235 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.0744. Min Act: -0.0000

Data Index: 1567624 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.3159. Min Act: -0.0000

Data Index: 1534767 (Python Code)

Max Activating Token Index: 366

Text #10

Max Range: 8.9360. Min Range: -8.9360

Max Act: 8.3440. Min Act: -0.0000

Data Index: 1615767 (Python Code)

Max Activating Token Index: 898

Text #11

Max Range: 8.9360. Min Range: -8.9360

Max Act: 7.8981. Min Act: -0.0000

Data Index: 1653909 (Python Code)

Max Activating Token Index: 459

Text #12

Max Range: 8.9360. Min Range: -8.9360

Max Act: 7.9942. Min Act: -0.0000

Data Index: 1606234 (Python Code)

Max Activating Token Index: 354

Text #13

Max Range: 8.9360. Min Range: -8.9360

Max Act: 7.5257. Min Act: -0.0000

Data Index: 1433479 (Python Code)

Max Activating Token Index: 166

Text #14

Max Range: 8.9360. Min Range: -8.9360

Max Act: 7.3463. Min Act: -0.0000

Data Index: 1483196 (Python Code)

Max Activating Token Index: 361

Text #15

Max Range: 8.9360. Min Range: -8.9360

Max Act: 7.4173. Min Act: -0.0000

Data Index: 1544476 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 8.9360. Min Range: -8.9360

Max Act: 6.3634. Min Act: -0.0000

Data Index: 1391438 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 8.9360. Min Range: -8.9360

Max Act: 6.6939. Min Act: -0.0000

Data Index: 1409179 (Python Code)

Max Activating Token Index: 813

Text #18

Max Range: 8.9360. Min Range: -8.9360

Max Act: 6.4864. Min Act: -0.0000

Data Index: 1565780 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 8.9360. Min Range: -8.9360

Max Act: 6.2533. Min Act: -0.0000

Data Index: 1549241 (Python Code)

Max Activating Token Index: 491