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

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

Neuron 2580 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.4099. Min Act: 0.0001

Data Index: 555468 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3605. Min Act: -0.0001

Data Index: 972233 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3385. Min Act: -0.0001

Data Index: 733604 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3425. Min Act: -0.0001

Data Index: 318918 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3476. Min Act: -0.0001

Data Index: 807645 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3122. Min Act: -0.0001

Data Index: 1323021 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3146. Min Act: -0.0001

Data Index: 1347913 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3002. Min Act: -0.0001

Data Index: 835756 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1069213 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3003. Min Act: -0.0001

Data Index: 925809 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3042. Min Act: -0.0001

Data Index: 759643 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3224. Min Act: -0.0001

Data Index: 110716 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2872. Min Act: -0.0001

Data Index: 538716 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1252646 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3057. Min Act: -0.0001

Data Index: 543736 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2791. Min Act: -0.0000

Data Index: 565628 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2922. Min Act: -0.0000

Data Index: 721704 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2730. Min Act: -0.0001

Data Index: 999905 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2681. Min Act: -0.0000

Data Index: 197075 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2649. Min Act: -0.0001

Data Index: 1066537 (C4 (Web Text))

Max Activating Token Index: 525