Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 442 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0837. Min Act: -0.0002

Data Index: 345616 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0754. Min Act: -0.0002

Data Index: 756324 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0691. Min Act: -0.0002

Data Index: 949680 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0714. Min Act: -0.0002

Data Index: 662298 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0675. Min Act: -0.0002

Data Index: 992133 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0644. Min Act: -0.0002

Data Index: 66365 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1291260 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0625. Min Act: -0.0002

Data Index: 887238 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0641. Min Act: -0.0002

Data Index: 993942 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0593. Min Act: -0.0002

Data Index: 65875 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1113611 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0580. Min Act: -0.0002

Data Index: 429649 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0571. Min Act: -0.0002

Data Index: 788442 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0575. Min Act: -0.0002

Data Index: 679657 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0575. Min Act: -0.0002

Data Index: 175593 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0581. Min Act: -0.0002

Data Index: 957560 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1089769 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1252160 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1112667 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0563. Min Act: -0.0001

Data Index: 97479 (C4 (Web Text))

Max Activating Token Index: 734