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

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

Neuron 5101 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3441. Min Range: -4.3441

Max Act: 4.1590. Min Act: -0.0001

Data Index: 550319 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 4.3441. Min Range: -4.3441

Max Act: 4.3441. Min Act: -0.0000

Data Index: 1416798 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.3200. Min Act: -0.0001

Data Index: 150262 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.4085. Min Act: -0.0001

Data Index: 1587191 (Python Code)

Max Activating Token Index: 860

Text #4

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.3471. Min Act: -0.0001

Data Index: 1541532 (Python Code)

Max Activating Token Index: 365

Text #5

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.4996. Min Act: -0.0001

Data Index: 1154917 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.1490. Min Act: -0.0001

Data Index: 64280 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 4.3441. Min Range: -4.3441

Max Act: 2.8262. Min Act: -0.0001

Data Index: 1596464 (Python Code)

Max Activating Token Index: 178

Text #8

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.7390. Min Act: -0.0001

Data Index: 1306501 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.1620. Min Act: -0.0000

Data Index: 1600384 (Python Code)

Max Activating Token Index: 130

Text #10

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.3045. Min Act: -0.0000

Data Index: 1056747 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.5388. Min Act: -0.0001

Data Index: 1364839 (Python Code)

Max Activating Token Index: 312

Text #12

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.1809. Min Act: -0.0000

Data Index: 1372704 (Python Code)

Max Activating Token Index: 782

Text #13

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.5090. Min Act: -0.0000

Data Index: 1399354 (Python Code)

Max Activating Token Index: 648

Text #14

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.2554. Min Act: -0.0001

Data Index: 1109140 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.2724. Min Act: -0.0001

Data Index: 650023 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.4053. Min Act: -0.0001

Data Index: 416121 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 4.3441. Min Range: -4.3441

Max Act: 2.7767. Min Act: -0.0001

Data Index: 1613998 (Python Code)

Max Activating Token Index: 1006

Text #18

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.3075. Min Act: -0.0001

Data Index: 1354723 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 4.3441. Min Range: -4.3441

Max Act: 3.4435. Min Act: -0.0000

Data Index: 1559165 (Python Code)

Max Activating Token Index: 982