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

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

Neuron 687 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.7931. Min Act: -0.0000

Data Index: 1568528 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1443810 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1478159 (Python Code)

Max Activating Token Index: 368

Text #3

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1523251 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.8560. Min Act: -0.0000

Data Index: 762601 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1400736 (Python Code)

Max Activating Token Index: 790

Text #6

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1007505 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1561754 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.9621. Min Act: -0.0000

Data Index: 272976 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1567259 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1377788 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1466265 (Python Code)

Max Activating Token Index: 367

Text #12

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.7834. Min Act: 0.0000

Data Index: 297789 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1376098 (Python Code)

Max Activating Token Index: 402

Text #14

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1369116 (Python Code)

Max Activating Token Index: 691

Text #15

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1592175 (Python Code)

Max Activating Token Index: 927

Text #16

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1624470 (Python Code)

Max Activating Token Index: 285

Text #17

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1496120 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1099438 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1620866 (Python Code)

Max Activating Token Index: 486