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

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

Neuron 4458 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8967. Min Range: -5.8967

Max Act: 5.3661. Min Act: -0.0000

Data Index: 1301536 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 5.8967. Min Range: -5.8967

Max Act: 5.8967. Min Act: -0.0000

Data Index: 488591 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 5.8967. Min Range: -5.8967

Max Act: 5.5699. Min Act: -0.0000

Data Index: 313861 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 5.8967. Min Range: -5.8967

Max Act: 5.1054. Min Act: -0.0000

Data Index: 951062 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 5.8967. Min Range: -5.8967

Max Act: 5.2165. Min Act: -0.0000

Data Index: 1301159 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.9415. Min Act: -0.0000

Data Index: 928056 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.3848. Min Act: -0.0000

Data Index: 314006 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.3338. Min Act: -0.0000

Data Index: 817247 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.4852. Min Act: -0.0000

Data Index: 516223 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 5.8967. Min Range: -5.8967

Max Act: 5.1201. Min Act: -0.0000

Data Index: 565742 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.3787. Min Act: -0.0000

Data Index: 538372 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.7295. Min Act: -0.0000

Data Index: 1135857 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.3552. Min Act: -0.0000

Data Index: 727171 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.4525. Min Act: -0.0000

Data Index: 976956 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.2381. Min Act: -0.0000

Data Index: 742275 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.5646. Min Act: -0.0000

Data Index: 192156 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.1719. Min Act: -0.0000

Data Index: 407149 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.1520. Min Act: -0.0000

Data Index: 1544897 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.5345. Min Act: -0.0000

Data Index: 186869 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 5.8967. Min Range: -5.8967

Max Act: 4.3206. Min Act: -0.0000

Data Index: 547004 (C4 (Web Text))

Max Activating Token Index: 84