Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 550 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0002

Data Index: 118181 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0589. Min Act: -0.0002

Data Index: 270224 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0561. Min Act: -0.0002

Data Index: 565168 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0539. Min Act: -0.0002

Data Index: 717696 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0533. Min Act: -0.0002

Data Index: 457108 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0497. Min Act: -0.0002

Data Index: 470793 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0512. Min Act: -0.0002

Data Index: 783043 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1359445 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0509. Min Act: -0.0002

Data Index: 82050 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0485. Min Act: -0.0002

Data Index: 406495 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0487. Min Act: -0.0002

Data Index: 703562 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0475. Min Act: -0.0002

Data Index: 431601 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0463. Min Act: -0.0001

Data Index: 879241 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1307570 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0456. Min Act: -0.0002

Data Index: 264965 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0486. Min Act: -0.0002

Data Index: 270211 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1168678 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0453. Min Act: -0.0002

Data Index: 615363 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1189216 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1239136 (C4 (Web Text))

Max Activating Token Index: 959