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

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

Neuron 3472 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4435. Min Act: -0.0000

Data Index: 181344 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4673. Min Act: -0.0001

Data Index: 100034 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3935. Min Act: -0.0000

Data Index: 565023 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3499. Min Act: -0.0001

Data Index: 838729 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3820. Min Act: -0.0000

Data Index: 585013 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1114244 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2705. Min Act: -0.0000

Data Index: 97652 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2974. Min Act: -0.0001

Data Index: 1069822 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2416. Min Act: -0.0001

Data Index: 917289 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2419. Min Act: -0.0000

Data Index: 142971 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2207. Min Act: -0.0000

Data Index: 218994 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1194606 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2519. Min Act: -0.0000

Data Index: 293229 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2724. Min Act: -0.0001

Data Index: 359952 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2461. Min Act: -0.0001

Data Index: 19598 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2425. Min Act: -0.0000

Data Index: 341039 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1153387 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2613. Min Act: -0.0000

Data Index: 493950 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2426. Min Act: -0.0001

Data Index: 1019157 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2134. Min Act: -0.0001

Data Index: 235901 (C4 (Web Text))

Max Activating Token Index: 254