Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4832 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.6328. Min Act: -0.0000

Data Index: 1209527 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.5741. Min Act: -0.0000

Data Index: 586281 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.2853. Min Act: -0.0000

Data Index: 1060097 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.1981. Min Act: -0.0000

Data Index: 1111381 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.0518. Min Act: -0.0000

Data Index: 657363 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.0809. Min Act: -0.0000

Data Index: 486570 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.0790. Min Act: -0.0000

Data Index: 260116 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.0731. Min Act: -0.0000

Data Index: 498384 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.0331. Min Act: -0.0000

Data Index: 790898 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.0467. Min Act: -0.0000

Data Index: 588956 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.6328. Min Range: -1.6328

Max Act: 1.0114. Min Act: -0.0000

Data Index: 76738 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.6328. Min Range: -1.6328

Max Act: 0.9886. Min Act: -0.0000

Data Index: 551247 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.6328. Min Range: -1.6328

Max Act: 0.9790. Min Act: -0.0000

Data Index: 906901 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.6328. Min Range: -1.6328

Max Act: 0.9373. Min Act: -0.0000

Data Index: 209047 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 1.6328. Min Range: -1.6328

Max Act: 0.9468. Min Act: -0.0000

Data Index: 997952 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 1.6328. Min Range: -1.6328

Max Act: 0.8997. Min Act: -0.0000

Data Index: 261875 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 1.6328. Min Range: -1.6328

Max Act: 0.9260. Min Act: -0.0000

Data Index: 436980 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.6328. Min Range: -1.6328

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1320341 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.6328. Min Range: -1.6328

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1016755 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 1.6328. Min Range: -1.6328

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1055033 (C4 (Web Text))

Max Activating Token Index: 120