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

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

Neuron 2944 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: 1.4553. Min Range: -1.4553

Max Act: 1.4553. Min Act: -0.0000

Data Index: 134056 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.3562. Min Act: -0.0000

Data Index: 294115 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1220929 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.3425. Min Act: -0.0000

Data Index: 819906 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1043763 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.1658. Min Act: -0.0000

Data Index: 1320066 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.2244. Min Act: -0.0000

Data Index: 542817 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.1483. Min Act: -0.0000

Data Index: 318597 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.0884. Min Act: 0.0000

Data Index: 828506 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.0750. Min Act: -0.0000

Data Index: 225716 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.1487. Min Act: -0.0000

Data Index: 385707 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.1313. Min Act: -0.0000

Data Index: 962217 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.1037. Min Act: -0.0000

Data Index: 536000 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.0309. Min Act: -0.0000

Data Index: 684092 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.0699. Min Act: -0.0000

Data Index: 219066 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1309426 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1061703 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1135698 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1229892 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.4553. Min Range: -1.4553

Max Act: 1.0818. Min Act: -0.0000

Data Index: 95751 (C4 (Web Text))

Max Activating Token Index: 873