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

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

Neuron 1454 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.8867. Min Act: -0.0000

Data Index: 1015438 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.7763. Min Act: -0.0000

Data Index: 1104786 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.6895. Min Act: -0.0000

Data Index: 707667 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.5800. Min Act: -0.0000

Data Index: 516704 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.5949. Min Act: -0.0000

Data Index: 1209288 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.4494. Min Act: -0.0000

Data Index: 669775 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.5254. Min Act: -0.0000

Data Index: 809026 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.5202. Min Act: -0.0000

Data Index: 798187 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.5027. Min Act: -0.0000

Data Index: 673978 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.2198. Min Act: -0.0000

Data Index: 1020706 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.2969. Min Act: -0.0000

Data Index: 1318268 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.2083. Min Act: -0.0000

Data Index: 435989 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.2694. Min Act: -0.0000

Data Index: 829403 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.1947. Min Act: -0.0000

Data Index: 348488 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.1721. Min Act: -0.0000

Data Index: 1023148 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.0531. Min Act: -0.0000

Data Index: 1215996 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.1724. Min Act: -0.0000

Data Index: 916094 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.0331. Min Act: -0.0000

Data Index: 111678 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.2530. Min Act: -0.0000

Data Index: 632039 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 2.8867. Min Range: -2.8867

Max Act: 2.2601. Min Act: -0.0000

Data Index: 1314503 (C4 (Web Text))

Max Activating Token Index: 847