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

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

Neuron 4917 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.1873. Min Act: -0.0000

Data Index: 827029 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1097910 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1219056 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.0570. Min Act: -0.0000

Data Index: 1271893 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.1756. Min Act: -0.0000

Data Index: 356785 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1306800 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.0042. Min Act: -0.0000

Data Index: 378941 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9006. Min Act: -0.0000

Data Index: 749397 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.1261. Min Act: -0.0000

Data Index: 588473 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.8946. Min Act: -0.0000

Data Index: 348797 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.8769. Min Act: -0.0000

Data Index: 253299 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.8700. Min Act: -0.0000

Data Index: 18613 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1048652 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9307. Min Act: -0.0000

Data Index: 605037 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9759. Min Act: -0.0000

Data Index: 376210 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9118. Min Act: -0.0000

Data Index: 329641 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1104568 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9540. Min Act: -0.0000

Data Index: 254289 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9429. Min Act: -0.0000

Data Index: 361946 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.8957. Min Act: -0.0000

Data Index: 262144 (C4 (Web Text))

Max Activating Token Index: 142