Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2587 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1401. Min Act: -0.0001

Data Index: 467982 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1015. Min Act: -0.0001

Data Index: 104391 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1286596 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1568314 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0831. Min Act: -0.0001

Data Index: 150172 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0759. Min Act: -0.0001

Data Index: 753463 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0800. Min Act: -0.0001

Data Index: 827176 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1137268 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1058549 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0779. Min Act: -0.0001

Data Index: 510916 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1079605 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1133377 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0803. Min Act: -0.0001

Data Index: 625421 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0755. Min Act: -0.0001

Data Index: 928432 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1626496 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1111447 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0820. Min Act: -0.0001

Data Index: 597818 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1375988 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0800. Min Act: -0.0001

Data Index: 705667 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0757. Min Act: -0.0001

Data Index: 456742 (C4 (Web Text))

Max Activating Token Index: 720