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

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

Neuron 1184 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: 3.2882. Min Range: -3.2882

Max Act: 3.2882. Min Act: -0.0000

Data Index: 1225836 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 3.2882. Min Range: -3.2882

Max Act: 3.2858. Min Act: -0.0000

Data Index: 293607 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.2882. Min Range: -3.2882

Max Act: 3.0964. Min Act: -0.0000

Data Index: 1071987 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.9963. Min Act: -0.0000

Data Index: 1110080 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.9639. Min Act: -0.0000

Data Index: 1022745 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.9640. Min Act: -0.0000

Data Index: 963690 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.8869. Min Act: -0.0000

Data Index: 311655 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.8707. Min Act: -0.0000

Data Index: 56925 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.7225. Min Act: -0.0000

Data Index: 757499 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.8274. Min Act: -0.0000

Data Index: 719868 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.6664. Min Act: -0.0000

Data Index: 480125 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.7810. Min Act: -0.0000

Data Index: 105189 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.7452. Min Act: -0.0000

Data Index: 1122880 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.6107. Min Act: -0.0000

Data Index: 76819 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.5679. Min Act: -0.0000

Data Index: 787499 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.6932. Min Act: -0.0000

Data Index: 1014878 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.6877. Min Act: -0.0000

Data Index: 1067193 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.6958. Min Act: -0.0000

Data Index: 54197 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.6841. Min Act: -0.0000

Data Index: 471302 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 3.2882. Min Range: -3.2882

Max Act: 2.7684. Min Act: -0.0000

Data Index: 815559 (C4 (Web Text))

Max Activating Token Index: 937