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

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

Neuron 3230 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3699. Min Act: -0.0000

Data Index: 476450 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3528. Min Act: -0.0000

Data Index: 401045 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3202. Min Act: -0.0000

Data Index: 412994 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1390039 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2907. Min Act: -0.0000

Data Index: 977218 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1153461 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2880. Min Act: -0.0000

Data Index: 28430 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2916. Min Act: -0.0000

Data Index: 329282 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3075. Min Act: -0.0000

Data Index: 297140 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1369420 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1568931 (Python Code)

Max Activating Token Index: 540

Text #11

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1422240 (Python Code)

Max Activating Token Index: 299

Text #12

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1061220 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2791. Min Act: -0.0000

Data Index: 390869 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2728. Min Act: -0.0000

Data Index: 832581 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2662. Min Act: -0.0000

Data Index: 436295 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2748. Min Act: -0.0000

Data Index: 210940 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1117203 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1163672 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1420858 (Python Code)

Max Activating Token Index: 942