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

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

Neuron 5518 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1465. Min Range: -2.1465

Max Act: 2.1198. Min Act: -0.0000

Data Index: 455466 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 2.1465. Min Range: -2.1465

Max Act: 2.1333. Min Act: -0.0000

Data Index: 427812 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 2.1465. Min Range: -2.1465

Max Act: 2.1052. Min Act: -0.0000

Data Index: 588852 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9717. Min Act: -0.0000

Data Index: 962422 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 2.1465. Min Range: -2.1465

Max Act: 2.0409. Min Act: -0.0000

Data Index: 299992 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 2.1465. Min Range: -2.1465

Max Act: 2.0233. Min Act: -0.0000

Data Index: 183575 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 2.1465. Min Range: -2.1465

Max Act: 2.1465. Min Act: -0.0000

Data Index: 506126 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 2.1465. Min Range: -2.1465

Max Act: 2.0084. Min Act: -0.0000

Data Index: 1213211 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 2.1465. Min Range: -2.1465

Max Act: 2.1273. Min Act: -0.0000

Data Index: 65183 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.8835. Min Act: -0.0000

Data Index: 285964 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9882. Min Act: -0.0000

Data Index: 781515 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9640. Min Act: -0.0000

Data Index: 498249 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9776. Min Act: -0.0000

Data Index: 1247252 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9523. Min Act: -0.0000

Data Index: 120503 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9491. Min Act: -0.0000

Data Index: 994585 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9372. Min Act: -0.0000

Data Index: 483869 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9398. Min Act: -0.0000

Data Index: 990640 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.8115. Min Act: -0.0000

Data Index: 787160 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9101. Min Act: -0.0000

Data Index: 1133029 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 2.1465. Min Range: -2.1465

Max Act: 1.9050. Min Act: -0.0000

Data Index: 458131 (C4 (Web Text))

Max Activating Token Index: 687