Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4192 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.8179. Min Act: -0.0000

Data Index: 15574 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7776. Min Act: -0.0000

Data Index: 957773 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1286248 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7270. Min Act: 0.0000

Data Index: 530080 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7153. Min Act: -0.0000

Data Index: 217846 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6848. Min Act: -0.0000

Data Index: 541918 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6935. Min Act: -0.0000

Data Index: 160512 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1031124 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6925. Min Act: -0.0000

Data Index: 103719 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6647. Min Act: -0.0000

Data Index: 485156 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1091088 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6754. Min Act: -0.0000

Data Index: 301760 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6760. Min Act: -0.0000

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6981. Min Act: -0.0000

Data Index: 334041 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6103. Min Act: -0.0000

Data Index: 62524 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6915. Min Act: -0.0000

Data Index: 860913 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1084370 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1056467 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6649. Min Act: -0.0000

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 421