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

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

Neuron 4998 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: 2.2611. Min Range: -2.2611

Max Act: 2.1715. Min Act: -0.0000

Data Index: 1023650 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.2611. Min Act: -0.0000

Data Index: 655691 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1878. Min Act: -0.0000

Data Index: 202196 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.8229. Min Act: -0.0000

Data Index: 889937 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.9364. Min Act: -0.0000

Data Index: 443651 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.8585. Min Act: -0.0000

Data Index: 1300969 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.7670. Min Act: -0.0000

Data Index: 1076909 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.7150. Min Act: -0.0000

Data Index: 278480 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.6273. Min Act: -0.0000

Data Index: 937681 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.6118. Min Act: -0.0000

Data Index: 759513 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.5188. Min Act: -0.0000

Data Index: 137858 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.5805. Min Act: -0.0000

Data Index: 846373 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.5183. Min Act: -0.0000

Data Index: 795726 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.4311. Min Act: -0.0000

Data Index: 342441 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.3967. Min Act: -0.0000

Data Index: 793323 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.5032. Min Act: -0.0000

Data Index: 105674 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.3341. Min Act: -0.0000

Data Index: 162051 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.5005. Min Act: -0.0000

Data Index: 831979 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.4789. Min Act: -0.0000

Data Index: 450578 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 2.2611. Min Range: -2.2611

Max Act: 1.4866. Min Act: -0.0000

Data Index: 486669 (C4 (Web Text))

Max Activating Token Index: 13