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

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

Neuron 5958 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0883. Min Range: -7.0883

Max Act: 6.6105. Min Act: -0.0001

Data Index: 281110 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 7.0883. Min Range: -7.0883

Max Act: 6.3180. Min Act: -0.0000

Data Index: 811839 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 7.0883. Min Range: -7.0883

Max Act: 7.0883. Min Act: -0.0001

Data Index: 355549 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 7.0883. Min Range: -7.0883

Max Act: 6.8457. Min Act: -0.0001

Data Index: 923 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 7.0883. Min Range: -7.0883

Max Act: 6.2715. Min Act: -0.0001

Data Index: 972148 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.8886. Min Act: -0.0001

Data Index: 1184025 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 7.0883. Min Range: -7.0883

Max Act: 6.1948. Min Act: -0.0001

Data Index: 640596 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.9229. Min Act: -0.0001

Data Index: 821431 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.8684. Min Act: -0.0001

Data Index: 1298244 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.8115. Min Act: -0.0001

Data Index: 837618 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.8242. Min Act: -0.0001

Data Index: 151193 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 7.0883. Min Range: -7.0883

Max Act: 6.3539. Min Act: -0.0001

Data Index: 813675 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.8982. Min Act: -0.0000

Data Index: 990214 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.5256. Min Act: -0.0001

Data Index: 946346 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 7.0883. Min Range: -7.0883

Max Act: 6.0093. Min Act: -0.0001

Data Index: 544522 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.1348. Min Act: -0.0001

Data Index: 1344486 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.6423. Min Act: -0.0001

Data Index: 160086 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.8280. Min Act: -0.0000

Data Index: 1247742 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 7.0883. Min Range: -7.0883

Max Act: 6.1050. Min Act: -0.0001

Data Index: 13168 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 7.0883. Min Range: -7.0883

Max Act: 5.9032. Min Act: -0.0001

Data Index: 1254210 (C4 (Web Text))

Max Activating Token Index: 464