Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1963 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0830. Min Act: -0.0001

Data Index: 1152657 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0611. Min Act: -0.0001

Data Index: 512061 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0121. Min Act: -0.0001

Data Index: 291452 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0068. Min Act: -0.0001

Data Index: 255115 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0079. Min Act: -0.0001

Data Index: 572579 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0035. Min Act: -0.0001

Data Index: 298992 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0052. Min Act: -0.0001

Data Index: 235083 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0189. Min Act: -0.0001

Data Index: 1315768 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0605. Min Act: -0.0001

Data Index: 368576 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9793. Min Act: -0.0001

Data Index: 1311042 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0159. Min Act: -0.0001

Data Index: 282940 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0015. Min Act: -0.0001

Data Index: 548796 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0336. Min Act: -0.0001

Data Index: 811066 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9649. Min Act: -0.0001

Data Index: 710724 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0183. Min Act: -0.0001

Data Index: 190073 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9650. Min Act: -0.0001

Data Index: 920680 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9736. Min Act: -0.0001

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9455. Min Act: -0.0001

Data Index: 381916 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9473. Min Act: -0.0001

Data Index: 1331129 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.8966. Min Act: -0.0001

Data Index: 277429 (C4 (Web Text))

Max Activating Token Index: 866