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

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

Neuron 354 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5512. Min Act: -0.0002

Data Index: 492572 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4554. Min Act: -0.0002

Data Index: 1084096 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4501. Min Act: -0.0002

Data Index: 1503016 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4129. Min Act: -0.0002

Data Index: 1545809 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4048. Min Act: -0.0002

Data Index: 627656 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4259. Min Act: -0.0002

Data Index: 689791 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4082. Min Act: -0.0002

Data Index: 1376729 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3905. Min Act: -0.0002

Data Index: 1619664 (Python Code)

Max Activating Token Index: 751

Text #8

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3986. Min Act: -0.0002

Data Index: 1057446 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3961. Min Act: -0.0002

Data Index: 723615 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3748. Min Act: -0.0002

Data Index: 1000579 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3846. Min Act: -0.0003

Data Index: 1340418 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3519. Min Act: -0.0002

Data Index: 1603746 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3525. Min Act: -0.0002

Data Index: 1221489 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3375. Min Act: -0.0002

Data Index: 238263 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3256. Min Act: -0.0002

Data Index: 1078752 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3200. Min Act: -0.0002

Data Index: 1374475 (Python Code)

Max Activating Token Index: 637

Text #17

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.2968. Min Act: -0.0002

Data Index: 1458950 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3237. Min Act: -0.0002

Data Index: 208244 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.3077. Min Act: -0.0002

Data Index: 1438403 (Python Code)

Max Activating Token Index: 245