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

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

Neuron 4896 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.2600. Min Act: -0.0000

Data Index: 902380 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.3251. Min Act: -0.0000

Data Index: 484848 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.4041. Min Act: -0.0000

Data Index: 1226736 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.2140. Min Act: -0.0000

Data Index: 716513 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.2101. Min Act: -0.0000

Data Index: 304147 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.1262. Min Act: -0.0000

Data Index: 399406 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.1430. Min Act: -0.0000

Data Index: 501612 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9998. Min Act: -0.0000

Data Index: 367779 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9626. Min Act: -0.0000

Data Index: 166275 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9207. Min Act: -0.0000

Data Index: 937984 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9420. Min Act: -0.0000

Data Index: 564951 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9695. Min Act: -0.0000

Data Index: 68095 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8779. Min Act: -0.0000

Data Index: 853464 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8506. Min Act: -0.0000

Data Index: 908101 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8619. Min Act: -0.0000

Data Index: 335385 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9311. Min Act: -0.0000

Data Index: 153225 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9612. Min Act: -0.0000

Data Index: 502057 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1079938 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8544. Min Act: -0.0000

Data Index: 508695 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1309306 (C4 (Web Text))

Max Activating Token Index: 364