Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2281 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.4611. Min Act: -0.0000

Data Index: 849397 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1309492 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.4391. Min Act: -0.0000

Data Index: 78901 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1093261 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3809. Min Act: -0.0000

Data Index: 17402 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3373. Min Act: -0.0000

Data Index: 836590 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3332. Min Act: -0.0000

Data Index: 980645 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1262208 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3259. Min Act: -0.0000

Data Index: 352970 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3098. Min Act: -0.0000

Data Index: 192440 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1214499 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3261. Min Act: -0.0001

Data Index: 197599 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1175063 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1290070 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3000. Min Act: -0.0001

Data Index: 110221 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3007. Min Act: -0.0000

Data Index: 188326 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.2964. Min Act: -0.0000

Data Index: 514611 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1358601 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.2828. Min Act: -0.0000

Data Index: 823890 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.2821. Min Act: -0.0000

Data Index: 649859 (C4 (Web Text))

Max Activating Token Index: 27