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

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

Neuron 4753 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.4075. Min Act: -0.0000

Data Index: 1122088 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.8694. Min Act: -0.0000

Data Index: 793421 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.9456. Min Act: -0.0001

Data Index: 820429 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.9877. Min Act: -0.0000

Data Index: 825826 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7889. Min Act: -0.0001

Data Index: 1331875 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7512. Min Act: -0.0000

Data Index: 62672 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7864. Min Act: -0.0001

Data Index: 661003 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1108219 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.8840. Min Act: -0.0000

Data Index: 920468 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7764. Min Act: -0.0001

Data Index: 572929 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7208. Min Act: -0.0001

Data Index: 210511 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1347958 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7604. Min Act: -0.0000

Data Index: 445223 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.6808. Min Act: -0.0000

Data Index: 305230 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.6979. Min Act: -0.0001

Data Index: 671599 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7220. Min Act: -0.0000

Data Index: 924233 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.7063. Min Act: -0.0001

Data Index: 189537 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.6664. Min Act: -0.0001

Data Index: 716673 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.6202. Min Act: -0.0001

Data Index: 644832 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.4075. Min Range: -1.4075

Max Act: 0.6371. Min Act: -0.0001

Data Index: 922541 (C4 (Web Text))

Max Activating Token Index: 450