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

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

Neuron 5138 in Layer 0

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: 0.1059. Min Range: -0.1059

Max Act: 0.1059. Min Act: -0.0001

Data Index: 865666 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0976. Min Act: -0.0001

Data Index: 514497 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0973. Min Act: -0.0001

Data Index: 243558 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0901. Min Act: -0.0001

Data Index: 92664 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0854. Min Act: -0.0001

Data Index: 284274 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0843. Min Act: -0.0001

Data Index: 43839 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0851. Min Act: -0.0001

Data Index: 792342 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0818. Min Act: -0.0001

Data Index: 798633 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1331795 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1217572 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0835. Min Act: -0.0001

Data Index: 568632 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0823. Min Act: -0.0001

Data Index: 820265 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0829. Min Act: -0.0001

Data Index: 670144 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1152751 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0796. Min Act: -0.0001

Data Index: 867895 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1215085 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1327922 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0781. Min Act: -0.0002

Data Index: 555058 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0794. Min Act: -0.0001

Data Index: 212615 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0776. Min Act: -0.0001

Data Index: 454569 (C4 (Web Text))

Max Activating Token Index: 350