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

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

Neuron 740 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8679. Min Range: -3.8679

Max Act: 3.8679. Min Act: -0.0001

Data Index: 638295 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 3.8679. Min Range: -3.8679

Max Act: 3.3926. Min Act: -0.0001

Data Index: 201671 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 3.8679. Min Range: -3.8679

Max Act: 3.0579. Min Act: -0.0001

Data Index: 1093210 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 3.8679. Min Range: -3.8679

Max Act: 3.0670. Min Act: -0.0001

Data Index: 457501 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.4705. Min Act: -0.0001

Data Index: 960972 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.9740. Min Act: -0.0001

Data Index: 1241330 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.9762. Min Act: -0.0001

Data Index: 693233 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.9880. Min Act: -0.0001

Data Index: 1329580 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.7915. Min Act: -0.0001

Data Index: 119322 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.9156. Min Act: -0.0001

Data Index: 70991 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.4294. Min Act: -0.0001

Data Index: 133869 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.7134. Min Act: -0.0001

Data Index: 389943 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.7026. Min Act: -0.0001

Data Index: 411985 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.6298. Min Act: -0.0001

Data Index: 929887 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.6059. Min Act: -0.0001

Data Index: 833631 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.4093. Min Act: -0.0001

Data Index: 863137 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.5122. Min Act: -0.0000

Data Index: 814610 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.4601. Min Act: -0.0001

Data Index: 1280892 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.3322. Min Act: -0.0000

Data Index: 406119 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 3.8679. Min Range: -3.8679

Max Act: 2.6744. Min Act: -0.0001

Data Index: 1135384 (C4 (Web Text))

Max Activating Token Index: 73