Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2831. Min Act: -0.0001

Data Index: 654667 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2476. Min Act: -0.0001

Data Index: 1462440 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2361. Min Act: -0.0001

Data Index: 420123 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1454904 (Python Code)

Max Activating Token Index: 843

Text #4

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2512. Min Act: -0.0001

Data Index: 861377 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2493. Min Act: -0.0001

Data Index: 1235210 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2145. Min Act: -0.0001

Data Index: 934926 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1301113 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1225015 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2285. Min Act: -0.0001

Data Index: 746147 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1618763 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1177230 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1084227 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2082. Min Act: -0.0001

Data Index: 22490 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2331. Min Act: -0.0001

Data Index: 1455438 (Python Code)

Max Activating Token Index: 325

Text #15

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1521095 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2228. Min Act: -0.0001

Data Index: 1496736 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2059. Min Act: -0.0001

Data Index: 969877 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2074. Min Act: -0.0001

Data Index: 252361 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2037. Min Act: -0.0001

Data Index: 1539982 (Python Code)

Max Activating Token Index: 812