Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1287 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1181. Min Act: -0.0000

Data Index: 145424 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1592937 (Python Code)

Max Activating Token Index: 679

Text #2

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1513250 (Python Code)

Max Activating Token Index: 724

Text #3

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1594163 (Python Code)

Max Activating Token Index: 940

Text #4

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1046666 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1024. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1631443 (Python Code)

Max Activating Token Index: 893

Text #7

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0909. Min Act: -0.0000

Data Index: 393312 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0849. Min Act: -0.0000

Data Index: 244701 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1565643 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0856. Min Act: -0.0000

Data Index: 643455 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0919. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0772. Min Act: -0.0000

Data Index: 833104 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1535460 (Python Code)

Max Activating Token Index: 659

Text #15

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1456171 (Python Code)

Max Activating Token Index: 874

Text #16

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0787. Min Act: -0.0000

Data Index: 125081 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1558106 (Python Code)

Max Activating Token Index: 396

Text #18

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0820. Min Act: -0.0000

Data Index: 632909 (C4 (Web Text))

Max Activating Token Index: 983