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

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

Neuron 3227 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: 0.6541. Min Range: -0.6541

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1198897 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6541. Min Act: -0.0000

Data Index: 410299 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6180. Min Act: -0.0000

Data Index: 156672 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1472649 (Python Code)

Max Activating Token Index: 972

Text #4

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5797. Min Act: -0.0000

Data Index: 308935 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5762. Min Act: -0.0000

Data Index: 266282 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1365202 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5296. Min Act: -0.0000

Data Index: 703437 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5642. Min Act: -0.0000

Data Index: 481143 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1204439 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5554. Min Act: -0.0000

Data Index: 82370 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5399. Min Act: -0.0000

Data Index: 981581 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5345. Min Act: -0.0000

Data Index: 322107 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1079440 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1630063 (Python Code)

Max Activating Token Index: 388

Text #15

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5136. Min Act: -0.0000

Data Index: 600516 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1634159 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1213163 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1161440 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1024054 (C4 (Web Text))

Max Activating Token Index: 355