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

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

Neuron 4721 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.2942. Min Act: -0.0001

Data Index: 954403 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.1245. Min Act: -0.0001

Data Index: 40189 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.1376. Min Act: -0.0001

Data Index: 923278 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.1324. Min Act: -0.0001

Data Index: 356042 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.1627. Min Act: -0.0001

Data Index: 312715 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 1.2942. Min Range: -1.2942

Max Act: 0.9965. Min Act: -0.0001

Data Index: 208655 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.1136. Min Act: -0.0001

Data Index: 46023 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0536. Min Act: -0.0001

Data Index: 705861 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.2942. Min Range: -1.2942

Max Act: 0.9664. Min Act: -0.0001

Data Index: 826878 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0673. Min Act: -0.0001

Data Index: 311028 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0627. Min Act: -0.0001

Data Index: 70444 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0958. Min Act: -0.0001

Data Index: 1345477 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0922. Min Act: -0.0001

Data Index: 340937 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.2942. Min Range: -1.2942

Max Act: 0.9850. Min Act: -0.0001

Data Index: 383804 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0414. Min Act: -0.0001

Data Index: 379780 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0324. Min Act: -0.0001

Data Index: 995889 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0944. Min Act: -0.0001

Data Index: 435277 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0090. Min Act: -0.0001

Data Index: 835703 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0381. Min Act: -0.0001

Data Index: 719404 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 1.2942. Min Range: -1.2942

Max Act: 1.0376. Min Act: -0.0001

Data Index: 965586 (C4 (Web Text))

Max Activating Token Index: 191