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

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

Neuron 419 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.7074. Min Act: -0.0001

Data Index: 858874 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.6149. Min Act: -0.0001

Data Index: 1448165 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.6112. Min Act: -0.0001

Data Index: 239568 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.6081. Min Act: -0.0001

Data Index: 1140982 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5222. Min Act: -0.0001

Data Index: 1372824 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5380. Min Act: -0.0001

Data Index: 27429 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5611. Min Act: -0.0001

Data Index: 1175273 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5224. Min Act: -0.0001

Data Index: 928530 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4897. Min Act: -0.0001

Data Index: 1419254 (Python Code)

Max Activating Token Index: 608

Text #9

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5508. Min Act: -0.0001

Data Index: 1622899 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4443. Min Act: -0.0001

Data Index: 745527 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4858. Min Act: -0.0001

Data Index: 1159352 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1242423 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4780. Min Act: -0.0001

Data Index: 1019607 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4741. Min Act: -0.0001

Data Index: 777378 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4905. Min Act: -0.0001

Data Index: 1191136 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4884. Min Act: -0.0001

Data Index: 805434 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5000. Min Act: -0.0001

Data Index: 234467 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4903. Min Act: -0.0001

Data Index: 868806 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4639. Min Act: -0.0001

Data Index: 511081 (C4 (Web Text))

Max Activating Token Index: 645