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

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

Neuron 5187 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.4564. Min Act: -0.0000

Data Index: 337316 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.1760. Min Act: -0.0000

Data Index: 1268659 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.1621. Min Act: -0.0000

Data Index: 930554 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1037460 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.0649. Min Act: -0.0000

Data Index: 117205 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.0145. Min Act: -0.0000

Data Index: 237823 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.9732. Min Act: -0.0000

Data Index: 768275 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.9817. Min Act: -0.0000

Data Index: 265300 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.9319. Min Act: -0.0000

Data Index: 991081 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.9258. Min Act: -0.0000

Data Index: 11463 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.9261. Min Act: -0.0000

Data Index: 138875 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.9080. Min Act: -0.0000

Data Index: 357605 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1219632 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1019842 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.8937. Min Act: -0.0000

Data Index: 585379 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.8585. Min Act: -0.0000

Data Index: 851360 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1419596 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.8646. Min Act: -0.0000

Data Index: 865858 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.7750. Min Act: -0.0000

Data Index: 620016 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 1.4564. Min Range: -1.4564

Max Act: 0.8589. Min Act: -0.0000

Data Index: 343678 (C4 (Web Text))

Max Activating Token Index: 953