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

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

Neuron 5940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.4251. Min Act: -0.0001

Data Index: 1475133 (Python Code)

Max Activating Token Index: 846

Text #1

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.2752. Min Act: -0.0001

Data Index: 1503208 (Python Code)

Max Activating Token Index: 369

Text #2

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.2583. Min Act: -0.0001

Data Index: 1443731 (Python Code)

Max Activating Token Index: 492

Text #3

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.5132. Min Act: -0.0001

Data Index: 1648503 (Python Code)

Max Activating Token Index: 808

Text #4

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.2754. Min Act: -0.0001

Data Index: 1554455 (Python Code)

Max Activating Token Index: 97

Text #5

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.0932. Min Act: -0.0001

Data Index: 1656795 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.3831. Min Act: -0.0001

Data Index: 991592 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.2353. Min Act: -0.0001

Data Index: 1577421 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.2093. Min Act: -0.0001

Data Index: 1459320 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.1132. Min Act: -0.0001

Data Index: 1525281 (Python Code)

Max Activating Token Index: 329

Text #10

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.1912. Min Act: -0.0001

Data Index: 1562052 (Python Code)

Max Activating Token Index: 895

Text #11

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.0016. Min Act: -0.0001

Data Index: 1467587 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 3.5132. Min Range: -3.5132

Max Act: 2.9912. Min Act: -0.0001

Data Index: 1604993 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 3.5132. Min Range: -3.5132

Max Act: 3.0567. Min Act: -0.0001

Data Index: 1512264 (Python Code)

Max Activating Token Index: 506

Text #14

Max Range: 3.5132. Min Range: -3.5132

Max Act: 2.7009. Min Act: -0.0001

Data Index: 1580677 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 3.5132. Min Range: -3.5132

Max Act: 2.8348. Min Act: -0.0001

Data Index: 1099216 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 3.5132. Min Range: -3.5132

Max Act: 2.8346. Min Act: -0.0001

Data Index: 1589344 (Python Code)

Max Activating Token Index: 69

Text #17

Max Range: 3.5132. Min Range: -3.5132

Max Act: 2.5612. Min Act: -0.0001

Data Index: 1553915 (Python Code)

Max Activating Token Index: 537

Text #18

Max Range: 3.5132. Min Range: -3.5132

Max Act: 2.5266. Min Act: -0.0001

Data Index: 1483423 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 3.5132. Min Range: -3.5132

Max Act: 2.5255. Min Act: -0.0001

Data Index: 1584300 (Python Code)

Max Activating Token Index: 608