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

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

Neuron 2703 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: 0.8749. Min Range: -0.8749

Max Act: 0.8749. Min Act: -0.0001

Data Index: 1475907 (Python Code)

Max Activating Token Index: 453

Text #1

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7962. Min Act: -0.0001

Data Index: 1493768 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7803. Min Act: -0.0001

Data Index: 1558054 (Python Code)

Max Activating Token Index: 199

Text #3

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.5574. Min Act: -0.0001

Data Index: 938626 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7347. Min Act: -0.0001

Data Index: 278649 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7229. Min Act: -0.0001

Data Index: 1611343 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6804. Min Act: -0.0001

Data Index: 1098206 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7269. Min Act: -0.0001

Data Index: 668846 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6314. Min Act: -0.0001

Data Index: 1454097 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.4256. Min Act: -0.0001

Data Index: 925601 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7627. Min Act: -0.0001

Data Index: 459590 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1430787 (Python Code)

Max Activating Token Index: 222

Text #12

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6865. Min Act: -0.0001

Data Index: 1112384 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6383. Min Act: -0.0001

Data Index: 1412430 (Python Code)

Max Activating Token Index: 393

Text #14

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6415. Min Act: -0.0001

Data Index: 456228 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6837. Min Act: -0.0001

Data Index: 1517514 (Python Code)

Max Activating Token Index: 130

Text #16

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6798. Min Act: -0.0001

Data Index: 1655810 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.5837. Min Act: -0.0001

Data Index: 1390719 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6494. Min Act: -0.0001

Data Index: 13743 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7034. Min Act: -0.0001

Data Index: 1603018 (Python Code)

Max Activating Token Index: 178