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

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

Neuron 14 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0003

Data Index: 1142333 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1130. Min Act: -0.0002

Data Index: 854452 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1319870 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1089. Min Act: -0.0002

Data Index: 942058 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1031. Min Act: -0.0002

Data Index: 677282 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1041. Min Act: -0.0002

Data Index: 1305057 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1007. Min Act: -0.0002

Data Index: 347500 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0929. Min Act: -0.0002

Data Index: 839130 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0916. Min Act: -0.0002

Data Index: 34261 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0897. Min Act: -0.0002

Data Index: 112273 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1243546 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1121750 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0870. Min Act: -0.0002

Data Index: 439485 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0864. Min Act: -0.0002

Data Index: 349792 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1096034 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1196448 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1114035 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1151662 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1253712 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0814. Min Act: -0.0002

Data Index: 372358 (C4 (Web Text))

Max Activating Token Index: 140