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

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

Neuron 3297 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1507670 (Python Code)

Max Activating Token Index: 426

Text #1

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2192. Min Act: -0.0001

Data Index: 1266520 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1929. Min Act: -0.0001

Data Index: 1318170 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2334. Min Act: -0.0001

Data Index: 1081736 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2126. Min Act: -0.0001

Data Index: 278237 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2179. Min Act: -0.0001

Data Index: 225996 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1272411 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2308. Min Act: -0.0001

Data Index: 243577 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1969. Min Act: -0.0001

Data Index: 261291 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1807. Min Act: -0.0001

Data Index: 608197 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1944. Min Act: -0.0001

Data Index: 425379 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1934. Min Act: -0.0001

Data Index: 922250 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1925. Min Act: -0.0001

Data Index: 273331 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1546. Min Act: -0.0001

Data Index: 66227 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1146706 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1940. Min Act: -0.0001

Data Index: 875708 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1151948 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1254666 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1308654 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.1775. Min Act: -0.0001

Data Index: 1212983 (C4 (Web Text))

Max Activating Token Index: 44