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

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

Neuron 464 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: 0.4571. Min Range: -0.4571

Max Act: 0.4431. Min Act: -0.0001

Data Index: 99465 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.4571. Min Act: -0.0001

Data Index: 71060 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3461. Min Act: -0.0001

Data Index: 1110314 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3006. Min Act: -0.0001

Data Index: 1148966 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2931. Min Act: -0.0001

Data Index: 887257 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3518. Min Act: -0.0001

Data Index: 742447 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3003. Min Act: -0.0000

Data Index: 356328 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3030. Min Act: -0.0001

Data Index: 40521 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2972. Min Act: -0.0001

Data Index: 497787 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2962. Min Act: -0.0001

Data Index: 397170 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2918. Min Act: -0.0000

Data Index: 441518 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2804. Min Act: -0.0001

Data Index: 4801 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2884. Min Act: -0.0001

Data Index: 1262013 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2828. Min Act: -0.0000

Data Index: 271721 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1058672 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2580. Min Act: -0.0000

Data Index: 393897 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2807. Min Act: -0.0001

Data Index: 1071278 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2768. Min Act: -0.0000

Data Index: 521861 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2674. Min Act: -0.0001

Data Index: 935293 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2422. Min Act: -0.0001

Data Index: 264422 (C4 (Web Text))

Max Activating Token Index: 884