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

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

Neuron 5145 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6277. Min Range: -2.6277

Max Act: 2.6277. Min Act: -0.0000

Data Index: 1476123 (Python Code)

Max Activating Token Index: 810

Text #1

Max Range: 2.6277. Min Range: -2.6277

Max Act: 2.4030. Min Act: -0.0000

Data Index: 1589371 (Python Code)

Max Activating Token Index: 829

Text #2

Max Range: 2.6277. Min Range: -2.6277

Max Act: 2.0732. Min Act: -0.0000

Data Index: 1554917 (Python Code)

Max Activating Token Index: 971

Text #3

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.9772. Min Act: -0.0000

Data Index: 1489206 (Python Code)

Max Activating Token Index: 166

Text #4

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.9227. Min Act: -0.0000

Data Index: 1582680 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.7804. Min Act: -0.0000

Data Index: 1502772 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.8228. Min Act: -0.0000

Data Index: 1481698 (Python Code)

Max Activating Token Index: 330

Text #7

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.7920. Min Act: -0.0000

Data Index: 1617880 (Python Code)

Max Activating Token Index: 742

Text #8

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.7485. Min Act: -0.0000

Data Index: 1444159 (Python Code)

Max Activating Token Index: 288

Text #9

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.7130. Min Act: -0.0000

Data Index: 1487226 (Python Code)

Max Activating Token Index: 587

Text #10

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.6631. Min Act: -0.0000

Data Index: 1421364 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.7622. Min Act: -0.0000

Data Index: 1432123 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.5667. Min Act: -0.0000

Data Index: 1473708 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.6128. Min Act: -0.0000

Data Index: 1645492 (Python Code)

Max Activating Token Index: 181

Text #14

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.5558. Min Act: -0.0000

Data Index: 1502528 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.5374. Min Act: -0.0000

Data Index: 1521272 (Python Code)

Max Activating Token Index: 450

Text #16

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1504713 (Python Code)

Max Activating Token Index: 591

Text #17

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1505524 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.4412. Min Act: -0.0000

Data Index: 1531023 (Python Code)

Max Activating Token Index: 245

Text #19

Max Range: 2.6277. Min Range: -2.6277

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1628843 (Python Code)

Max Activating Token Index: 611