Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3904 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3386. Min Act: 0.0000

Data Index: 300972 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3289. Min Act: 0.0001

Data Index: 1212717 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3321. Min Act: -0.0000

Data Index: 860943 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3205. Min Act: -0.0000

Data Index: 481 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3145. Min Act: -0.0000

Data Index: 109413 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2964. Min Act: -0.0000

Data Index: 421669 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3023. Min Act: 0.0001

Data Index: 994227 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3007. Min Act: -0.0000

Data Index: 585944 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2876. Min Act: 0.0000

Data Index: 785603 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2987. Min Act: -0.0000

Data Index: 331798 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2854. Min Act: -0.0000

Data Index: 363780 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2834. Min Act: 0.0000

Data Index: 1236193 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1250256 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2898. Min Act: 0.0001

Data Index: 643952 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2629. Min Act: 0.0000

Data Index: 1266774 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3098. Min Act: -0.0000

Data Index: 861760 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2726. Min Act: -0.0000

Data Index: 899645 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2592. Min Act: 0.0000

Data Index: 405463 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2595. Min Act: -0.0000

Data Index: 413849 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2784. Min Act: 0.0000

Data Index: 587566 (C4 (Web Text))

Max Activating Token Index: 75