Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4284 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9327. Min Range: -3.9327

Max Act: 3.9327. Min Act: -0.0000

Data Index: 367257 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 3.9327. Min Range: -3.9327

Max Act: 3.8439. Min Act: -0.0000

Data Index: 1100037 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 3.9327. Min Range: -3.9327

Max Act: 3.8884. Min Act: -0.0000

Data Index: 1227091 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.9327. Min Range: -3.9327

Max Act: 3.5497. Min Act: -0.0000

Data Index: 49162 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 3.9327. Min Range: -3.9327

Max Act: 3.4827. Min Act: -0.0000

Data Index: 1018221 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 3.9327. Min Range: -3.9327

Max Act: 3.1579. Min Act: -0.0000

Data Index: 1082694 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 3.9327. Min Range: -3.9327

Max Act: 3.0654. Min Act: -0.0000

Data Index: 686835 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 3.9327. Min Range: -3.9327

Max Act: 2.8118. Min Act: -0.0000

Data Index: 53721 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 3.9327. Min Range: -3.9327

Max Act: 2.1471. Min Act: -0.0000

Data Index: 669425 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 3.9327. Min Range: -3.9327

Max Act: 2.2268. Min Act: -0.0000

Data Index: 1346881 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 3.9327. Min Range: -3.9327

Max Act: 2.1917. Min Act: -0.0000

Data Index: 71291 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 3.9327. Min Range: -3.9327

Max Act: 2.1170. Min Act: -0.0000

Data Index: 1289263 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 3.9327. Min Range: -3.9327

Max Act: 2.1012. Min Act: -0.0000

Data Index: 1123272 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.9365. Min Act: -0.0000

Data Index: 941036 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1493144 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.9410. Min Act: -0.0000

Data Index: 1466660 (Python Code)

Max Activating Token Index: 1011

Text #16

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.8059. Min Act: -0.0000

Data Index: 975606 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.9092. Min Act: -0.0000

Data Index: 191305 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.8927. Min Act: -0.0000

Data Index: 1032536 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.8794. Min Act: -0.0000

Data Index: 579280 (C4 (Web Text))

Max Activating Token Index: 437