Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3407 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1032647 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4506. Min Act: -0.0001

Data Index: 562394 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1323803 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4375. Min Act: -0.0000

Data Index: 993984 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1296442 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3984. Min Act: -0.0001

Data Index: 524874 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4160. Min Act: -0.0001

Data Index: 748787 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4269. Min Act: -0.0000

Data Index: 732615 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4210. Min Act: -0.0000

Data Index: 465244 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4077. Min Act: -0.0001

Data Index: 1245970 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4095. Min Act: -0.0000

Data Index: 453450 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4180. Min Act: -0.0001

Data Index: 963380 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4497. Min Act: -0.0001

Data Index: 389105 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3730. Min Act: -0.0001

Data Index: 47269 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4307. Min Act: -0.0001

Data Index: 638502 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1298160 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4038. Min Act: -0.0001

Data Index: 279347 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1336273 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4065. Min Act: -0.0001

Data Index: 1001389 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3662. Min Act: -0.0001

Data Index: 846119 (C4 (Web Text))

Max Activating Token Index: 267