Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 199 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.3423. Min Act: -0.0001

Data Index: 42571 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.3019. Min Act: -0.0001

Data Index: 771005 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.3076. Min Act: -0.0001

Data Index: 1101102 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.2439. Min Act: -0.0001

Data Index: 1221626 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.1805. Min Act: -0.0001

Data Index: 1196766 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.1422. Min Act: -0.0001

Data Index: 1120202 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0812. Min Act: -0.0001

Data Index: 217308 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0967. Min Act: -0.0001

Data Index: 1212764 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0605. Min Act: -0.0001

Data Index: 766149 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0692. Min Act: -0.0001

Data Index: 283708 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0529. Min Act: -0.0001

Data Index: 357958 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0165. Min Act: -0.0001

Data Index: 993970 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0417. Min Act: -0.0001

Data Index: 281047 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0376. Min Act: -0.0001

Data Index: 440237 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.3423. Min Range: -1.3423

Max Act: 0.9990. Min Act: -0.0001

Data Index: 1339633 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.3423. Min Range: -1.3423

Max Act: 0.9927. Min Act: -0.0001

Data Index: 68710 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0694. Min Act: -0.0001

Data Index: 1289065 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.3423. Min Range: -1.3423

Max Act: 0.9719. Min Act: -0.0001

Data Index: 1147816 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0650. Min Act: -0.0001

Data Index: 805565 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0330. Min Act: -0.0001

Data Index: 775694 (C4 (Web Text))

Max Activating Token Index: 376