Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 273 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.1649. Min Act: -0.0001

Data Index: 397404 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.1766. Min Act: -0.0001

Data Index: 689227 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.1476. Min Act: -0.0001

Data Index: 829898 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0328. Min Act: -0.0001

Data Index: 311519 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9508. Min Act: -0.0001

Data Index: 703760 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0215. Min Act: -0.0001

Data Index: 107363 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8987. Min Act: -0.0001

Data Index: 956590 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8226. Min Act: -0.0001

Data Index: 807687 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8595. Min Act: -0.0001

Data Index: 1206480 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8470. Min Act: -0.0001

Data Index: 1108149 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9008. Min Act: -0.0001

Data Index: 222680 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8723. Min Act: -0.0001

Data Index: 348766 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8017. Min Act: -0.0001

Data Index: 850707 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8552. Min Act: -0.0001

Data Index: 158950 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.7969. Min Act: -0.0001

Data Index: 1105725 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8500. Min Act: -0.0001

Data Index: 581226 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8402. Min Act: -0.0001

Data Index: 1333613 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8635. Min Act: -0.0001

Data Index: 802810 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8875. Min Act: -0.0001

Data Index: 392128 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8358. Min Act: -0.0001

Data Index: 124246 (C4 (Web Text))

Max Activating Token Index: 918