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

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

Neuron 4209 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: 1.5116. Min Range: -1.5116

Max Act: 1.5116. Min Act: -0.0001

Data Index: 1013833 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.5116. Min Act: -0.0001

Data Index: 1372694 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.3842. Min Act: -0.0001

Data Index: 315527 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.2283. Min Act: -0.0001

Data Index: 1343213 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.3705. Min Act: -0.0001

Data Index: 1198331 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.1968. Min Act: -0.0001

Data Index: 880665 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.1740. Min Act: -0.0001

Data Index: 918549 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.3457. Min Act: -0.0001

Data Index: 880511 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.2278. Min Act: -0.0001

Data Index: 63392 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.2001. Min Act: -0.0001

Data Index: 1143878 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.1643. Min Act: -0.0001

Data Index: 520134 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.1191. Min Act: -0.0001

Data Index: 756299 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.0188. Min Act: -0.0001

Data Index: 530595 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.2620. Min Act: -0.0001

Data Index: 819982 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.0078. Min Act: -0.0001

Data Index: 1200340 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.0293. Min Act: -0.0001

Data Index: 198923 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.0780. Min Act: -0.0001

Data Index: 1335140 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 1.5116. Min Range: -1.5116

Max Act: 0.8862. Min Act: -0.0001

Data Index: 1001257 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.5116. Min Range: -1.5116

Max Act: 0.9885. Min Act: -0.0001

Data Index: 614624 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.5116. Min Range: -1.5116

Max Act: 0.9528. Min Act: -0.0001

Data Index: 436626 (C4 (Web Text))

Max Activating Token Index: 673