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

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

Neuron 5277 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.9951. Min Act: -0.0000

Data Index: 801317 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.9115. Min Act: -0.0000

Data Index: 34457 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.7336. Min Act: -0.0000

Data Index: 117276 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.7893. Min Act: -0.0000

Data Index: 959167 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.6821. Min Act: -0.0000

Data Index: 1429974 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.6669. Min Act: -0.0000

Data Index: 337760 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.6187. Min Act: -0.0000

Data Index: 398427 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.5845. Min Act: -0.0000

Data Index: 781144 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.6520. Min Act: -0.0000

Data Index: 624280 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.5357. Min Act: -0.0000

Data Index: 773594 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.5457. Min Act: -0.0000

Data Index: 1272822 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4258. Min Act: -0.0000

Data Index: 1479465 (Python Code)

Max Activating Token Index: 371

Text #12

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.5186. Min Act: -0.0000

Data Index: 269973 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.5927. Min Act: -0.0000

Data Index: 79730 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4999. Min Act: -0.0000

Data Index: 210479 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1116356 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4686. Min Act: -0.0000

Data Index: 1452715 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4640. Min Act: -0.0000

Data Index: 856534 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4647. Min Act: -0.0000

Data Index: 269277 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.3778. Min Act: -0.0000

Data Index: 545490 (C4 (Web Text))

Max Activating Token Index: 216