Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1440 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.5181. Min Act: -0.0000

Data Index: 1397286 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.3151. Min Act: -0.0000

Data Index: 540374 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.2942. Min Act: -0.0000

Data Index: 1585148 (Python Code)

Max Activating Token Index: 300

Text #3

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1566391 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.0864. Min Act: -0.0001

Data Index: 1577752 (Python Code)

Max Activating Token Index: 556

Text #5

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1522878 (Python Code)

Max Activating Token Index: 604

Text #6

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1402171 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1483545 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1605527 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1458430 (Python Code)

Max Activating Token Index: 953

Text #10

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.0550. Min Act: -0.0001

Data Index: 1320630 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.5181. Min Range: -1.5181

Max Act: 0.9855. Min Act: -0.0001

Data Index: 1557598 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 1.5181. Min Range: -1.5181

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1516187 (Python Code)

Max Activating Token Index: 670

Text #13

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1549632 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1591260 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 1.5181. Min Range: -1.5181

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1516317 (Python Code)

Max Activating Token Index: 804

Text #16

Max Range: 1.5181. Min Range: -1.5181

Max Act: 0.9879. Min Act: -0.0001

Data Index: 1567442 (Python Code)

Max Activating Token Index: 735

Text #17

Max Range: 1.5181. Min Range: -1.5181

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1519258 (Python Code)

Max Activating Token Index: 992

Text #18

Max Range: 1.5181. Min Range: -1.5181

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1612751 (Python Code)

Max Activating Token Index: 78

Text #19

Max Range: 1.5181. Min Range: -1.5181

Max Act: 0.9415. Min Act: -0.0001

Data Index: 1618480 (Python Code)

Max Activating Token Index: 300