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

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

Neuron 2869 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.1019. Min Act: -0.0002

Data Index: 70026 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.1035. Min Act: -0.0002

Data Index: 265023 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0494. Min Act: -0.0002

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0682. Min Act: -0.0002

Data Index: 1260723 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0550. Min Act: -0.0002

Data Index: 184008 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0729. Min Act: -0.0002

Data Index: 1656975 (Python Code)

Max Activating Token Index: 175

Text #6

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0594. Min Act: -0.0002

Data Index: 904289 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0309. Min Act: -0.0002

Data Index: 452939 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0111. Min Act: -0.0002

Data Index: 785643 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0346. Min Act: -0.0002

Data Index: 1319259 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0076. Min Act: -0.0002

Data Index: 145492 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0277. Min Act: -0.0002

Data Index: 319736 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0283. Min Act: -0.0002

Data Index: 511368 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.9907. Min Act: -0.0002

Data Index: 673933 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0110. Min Act: -0.0003

Data Index: 312299 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.9975. Min Act: -0.0002

Data Index: 763976 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.9891. Min Act: -0.0002

Data Index: 199515 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.0013. Min Act: -0.0002

Data Index: 718206 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.9981. Min Act: -0.0002

Data Index: 1320040 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.9998. Min Act: -0.0002

Data Index: 1089306 (C4 (Web Text))

Max Activating Token Index: 665