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

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

Neuron 4264 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0474. Min Range: -4.0474

Max Act: 4.0179. Min Act: -0.0000

Data Index: 136414 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 4.0474. Min Range: -4.0474

Max Act: 4.0474. Min Act: -0.0000

Data Index: 90444 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.3577. Min Act: -0.0000

Data Index: 764494 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.9438. Min Act: -0.0000

Data Index: 233080 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.4482. Min Act: -0.0000

Data Index: 778160 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.0948. Min Act: -0.0000

Data Index: 697115 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.3651. Min Act: -0.0000

Data Index: 1224031 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.4341. Min Act: -0.0000

Data Index: 576703 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 4.0474. Min Range: -4.0474

Max Act: 2.9703. Min Act: -0.0000

Data Index: 330558 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.0370. Min Act: -0.0000

Data Index: 953298 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.2422. Min Act: -0.0000

Data Index: 1071939 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.1135. Min Act: -0.0000

Data Index: 616022 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.1303. Min Act: -0.0000

Data Index: 62740 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 4.0474. Min Range: -4.0474

Max Act: 2.7835. Min Act: -0.0000

Data Index: 13821 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 4.0474. Min Range: -4.0474

Max Act: 2.9023. Min Act: -0.0000

Data Index: 50119 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 4.0474. Min Range: -4.0474

Max Act: 2.8782. Min Act: -0.0000

Data Index: 701675 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 4.0474. Min Range: -4.0474

Max Act: 2.5848. Min Act: -0.0000

Data Index: 1333785 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 4.0474. Min Range: -4.0474

Max Act: 2.6312. Min Act: -0.0000

Data Index: 439194 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 4.0474. Min Range: -4.0474

Max Act: 2.3613. Min Act: -0.0000

Data Index: 969918 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 4.0474. Min Range: -4.0474

Max Act: 2.5972. Min Act: -0.0000

Data Index: 1273774 (C4 (Web Text))

Max Activating Token Index: 262