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

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

Neuron 2248 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: 1.0987. Min Range: -1.0987

Max Act: 1.0867. Min Act: -0.0002

Data Index: 284677 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.0987. Min Range: -1.0987

Max Act: 1.0987. Min Act: -0.0002

Data Index: 677190 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.0987. Min Range: -1.0987

Max Act: 1.0768. Min Act: -0.0002

Data Index: 539162 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.0987. Min Range: -1.0987

Max Act: 1.0552. Min Act: -0.0002

Data Index: 945409 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.0987. Min Range: -1.0987

Max Act: 1.0394. Min Act: -0.0002

Data Index: 1458901 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 1.0987. Min Range: -1.0987

Max Act: 1.0454. Min Act: -0.0002

Data Index: 549942 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9929. Min Act: -0.0002

Data Index: 600710 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 1.0987. Min Range: -1.0987

Max Act: 1.0004. Min Act: -0.0002

Data Index: 731327 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9985. Min Act: -0.0002

Data Index: 14045 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9720. Min Act: -0.0002

Data Index: 630289 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9894. Min Act: -0.0002

Data Index: 947900 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9893. Min Act: -0.0002

Data Index: 1048015 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9809. Min Act: -0.0002

Data Index: 1058744 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9544. Min Act: -0.0002

Data Index: 572754 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9566. Min Act: -0.0002

Data Index: 509177 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9653. Min Act: -0.0002

Data Index: 654482 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9424. Min Act: -0.0002

Data Index: 77915 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9288. Min Act: -0.0002

Data Index: 1379500 (Python Code)

Max Activating Token Index: 552

Text #18

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9683. Min Act: -0.0002

Data Index: 486943 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9339. Min Act: -0.0002

Data Index: 1004103 (C4 (Web Text))

Max Activating Token Index: 12