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

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

Neuron 3017 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.9562. Min Act: -0.0000

Data Index: 389955 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1255728 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.9447. Min Act: -0.0000

Data Index: 157435 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.9991. Min Act: -0.0000

Data Index: 19634 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.9383. Min Act: -0.0000

Data Index: 397898 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8921. Min Act: -0.0000

Data Index: 603859 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1257833 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1215046 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1037095 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8173. Min Act: -0.0000

Data Index: 259558 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1350797 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1156080 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8278. Min Act: -0.0000

Data Index: 604632 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1245433 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7677. Min Act: -0.0000

Data Index: 825699 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7436. Min Act: -0.0001

Data Index: 352828 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1096308 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1351361 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1204684 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1010242 (C4 (Web Text))

Max Activating Token Index: 222