Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1833 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.4828. Min Range: -4.4828

Max Act: 4.4828. Min Act: -0.0000

Data Index: 1469670 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 4.4828. Min Range: -4.4828

Max Act: 4.0387. Min Act: -0.0001

Data Index: 1640506 (Python Code)

Max Activating Token Index: 910

Text #2

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.8009. Min Act: -0.0000

Data Index: 1394298 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.7324. Min Act: -0.0001

Data Index: 1581986 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.8037. Min Act: -0.0000

Data Index: 562365 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.9246. Min Act: -0.0000

Data Index: 218894 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.6661. Min Act: -0.0001

Data Index: 1490229 (Python Code)

Max Activating Token Index: 857

Text #7

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.6887. Min Act: -0.0000

Data Index: 1622259 (Python Code)

Max Activating Token Index: 333

Text #8

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.7773. Min Act: -0.0001

Data Index: 1600427 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.5997. Min Act: -0.0001

Data Index: 1630440 (Python Code)

Max Activating Token Index: 648

Text #10

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.3933. Min Act: -0.0000

Data Index: 1476051 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.5259. Min Act: -0.0000

Data Index: 1456131 (Python Code)

Max Activating Token Index: 1015

Text #12

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.5361. Min Act: -0.0000

Data Index: 1554465 (Python Code)

Max Activating Token Index: 353

Text #13

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.5423. Min Act: -0.0001

Data Index: 1603234 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.5140. Min Act: -0.0001

Data Index: 1646066 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.1490. Min Act: -0.0001

Data Index: 1488897 (Python Code)

Max Activating Token Index: 311

Text #16

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.3665. Min Act: -0.0000

Data Index: 1427040 (Python Code)

Max Activating Token Index: 296

Text #17

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.2224. Min Act: -0.0000

Data Index: 1401736 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.3462. Min Act: -0.0001

Data Index: 1278061 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 4.4828. Min Range: -4.4828

Max Act: 3.2144. Min Act: -0.0000

Data Index: 1633056 (Python Code)

Max Activating Token Index: 645