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

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

Neuron 2930 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.8913. Min Act: -0.0000

Data Index: 58457 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.2162. Min Act: -0.0000

Data Index: 440268 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.2939. Min Act: -0.0000

Data Index: 938167 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.1860. Min Act: -0.0000

Data Index: 409945 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1515984 (Python Code)

Max Activating Token Index: 644

Text #5

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.0279. Min Act: -0.0000

Data Index: 643140 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.0741. Min Act: -0.0000

Data Index: 108057 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1255266 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1181902 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.0174. Min Act: -0.0000

Data Index: 798139 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.8913. Min Range: -1.8913

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1462932 (Python Code)

Max Activating Token Index: 459

Text #11

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.9232. Min Act: -0.0000

Data Index: 338868 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.9356. Min Act: -0.0000

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1051828 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.8834. Min Act: -0.0000

Data Index: 750892 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1331082 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.9243. Min Act: -0.0000

Data Index: 641831 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.9178. Min Act: -0.0000

Data Index: 478351 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1399774 (Python Code)

Max Activating Token Index: 607

Text #19

Max Range: 1.8913. Min Range: -1.8913

Max Act: 0.9077. Min Act: -0.0000

Data Index: 472538 (C4 (Web Text))

Max Activating Token Index: 642