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

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

Neuron 4102 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6914. Min Act: -0.0000

Data Index: 1618874 (Python Code)

Max Activating Token Index: 716

Text #1

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.2483. Min Act: -0.0000

Data Index: 1103138 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.1637. Min Act: -0.0000

Data Index: 1529650 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4847. Min Act: -0.0000

Data Index: 563289 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.0686. Min Act: -0.0000

Data Index: 766493 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.3495. Min Act: -0.0000

Data Index: 1485505 (Python Code)

Max Activating Token Index: 242

Text #6

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.3050. Min Act: -0.0000

Data Index: 1369160 (Python Code)

Max Activating Token Index: 486

Text #7

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.2981. Min Act: -0.0000

Data Index: 805028 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.9456. Min Act: -0.0000

Data Index: 1463818 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.0306. Min Act: -0.0000

Data Index: 539994 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.9009. Min Act: -0.0000

Data Index: 1587242 (Python Code)

Max Activating Token Index: 773

Text #11

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.8974. Min Act: -0.0000

Data Index: 281549 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.7442. Min Act: -0.0000

Data Index: 689487 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.0062. Min Act: -0.0000

Data Index: 67497 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.7163. Min Act: -0.0000

Data Index: 1591185 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.9781. Min Act: -0.0000

Data Index: 741301 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.9255. Min Act: -0.0000

Data Index: 453472 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.7567. Min Act: -0.0000

Data Index: 628873 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.7304. Min Act: -0.0000

Data Index: 155943 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.7172. Min Act: -0.0000

Data Index: 1631954 (Python Code)

Max Activating Token Index: 472