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

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

Neuron 5167 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: 0.6955. Min Range: -0.6955

Max Act: 0.6955. Min Act: -0.0000

Data Index: 156214 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6904. Min Act: -0.0000

Data Index: 479343 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6168. Min Act: -0.0000

Data Index: 553002 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5618. Min Act: -0.0000

Data Index: 916718 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6050. Min Act: -0.0000

Data Index: 499927 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1184197 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1343435 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1122868 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4879. Min Act: -0.0000

Data Index: 196260 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5686. Min Act: -0.0000

Data Index: 857128 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1305502 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5635. Min Act: -0.0000

Data Index: 242395 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5407. Min Act: -0.0000

Data Index: 822604 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5495. Min Act: -0.0000

Data Index: 687699 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1186840 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5502. Min Act: -0.0000

Data Index: 790174 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5262. Min Act: -0.0000

Data Index: 333436 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5785. Min Act: -0.0000

Data Index: 177610 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5768. Min Act: -0.0000

Data Index: 248154 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5469. Min Act: -0.0000

Data Index: 204118 (C4 (Web Text))

Max Activating Token Index: 537