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

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

Neuron 3096 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: 0.2756. Min Range: -0.2756

Max Act: 0.2756. Min Act: -0.0001

Data Index: 683750 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2507. Min Act: -0.0001

Data Index: 510535 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2413. Min Act: -0.0001

Data Index: 1268025 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2377. Min Act: -0.0001

Data Index: 315187 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1044731 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2133. Min Act: -0.0001

Data Index: 385413 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2179. Min Act: -0.0001

Data Index: 407900 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2140. Min Act: -0.0001

Data Index: 211509 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1996. Min Act: -0.0001

Data Index: 398506 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2238. Min Act: -0.0001

Data Index: 577696 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2147. Min Act: -0.0001

Data Index: 97088 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2016. Min Act: -0.0001

Data Index: 1356562 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1939. Min Act: -0.0001

Data Index: 792700 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1745. Min Act: -0.0001

Data Index: 914370 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1214949 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1123131 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1932. Min Act: -0.0001

Data Index: 518390 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1057133 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1123417 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1330990 (C4 (Web Text))

Max Activating Token Index: 362