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

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

Neuron 2910 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: 3.7508. Min Range: -3.7508

Max Act: 3.7508. Min Act: -0.0000

Data Index: 229659 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.2567. Min Act: -0.0000

Data Index: 789692 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5533. Min Act: -0.0000

Data Index: 996956 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.1190. Min Act: -0.0000

Data Index: 621220 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.1066. Min Act: -0.0000

Data Index: 467272 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.2678. Min Act: -0.0000

Data Index: 455349 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4031. Min Act: -0.0000

Data Index: 285944 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.2680. Min Act: -0.0000

Data Index: 242882 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 3.7508. Min Range: -3.7508

Max Act: 2.9676. Min Act: -0.0000

Data Index: 142059 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 3.7508. Min Range: -3.7508

Max Act: 2.8339. Min Act: -0.0000

Data Index: 34525 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.2333. Min Act: -0.0000

Data Index: 1074861 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.0475. Min Act: -0.0000

Data Index: 1064033 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.0705. Min Act: -0.0000

Data Index: 359296 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 3.7508. Min Range: -3.7508

Max Act: 2.8815. Min Act: -0.0000

Data Index: 1185648 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.1554. Min Act: -0.0000

Data Index: 492779 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 3.7508. Min Range: -3.7508

Max Act: 2.9911. Min Act: -0.0000

Data Index: 1294963 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.7508. Min Range: -3.7508

Max Act: 2.9946. Min Act: -0.0000

Data Index: 949743 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 3.7508. Min Range: -3.7508

Max Act: 2.9757. Min Act: -0.0000

Data Index: 648615 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 3.7508. Min Range: -3.7508

Max Act: 2.7125. Min Act: -0.0000

Data Index: 491887 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 3.7508. Min Range: -3.7508

Max Act: 2.9817. Min Act: -0.0000

Data Index: 1240972 (C4 (Web Text))

Max Activating Token Index: 22