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

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

Neuron 5896 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: 3.7915. Min Range: -3.7915

Max Act: 3.7915. Min Act: -0.0002

Data Index: 365995 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6358. Min Act: -0.0003

Data Index: 867006 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4456. Min Act: -0.0003

Data Index: 1073326 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.5442. Min Act: -0.0002

Data Index: 941779 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4981. Min Act: -0.0002

Data Index: 996609 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4620. Min Act: -0.0003

Data Index: 827751 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4647. Min Act: -0.0002

Data Index: 896934 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.5239. Min Act: -0.0002

Data Index: 1016284 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4453. Min Act: -0.0002

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4704. Min Act: -0.0002

Data Index: 258649 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4693. Min Act: -0.0003

Data Index: 176990 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4442. Min Act: -0.0003

Data Index: 848264 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.3232. Min Act: -0.0002

Data Index: 851548 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4266. Min Act: -0.0002

Data Index: 807871 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.3372. Min Act: -0.0003

Data Index: 1233534 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4437. Min Act: -0.0003

Data Index: 1345566 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.3611. Min Act: -0.0002

Data Index: 434499 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.3255. Min Act: -0.0002

Data Index: 151153 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4138. Min Act: -0.0002

Data Index: 795450 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.4069. Min Act: -0.0002

Data Index: 960472 (C4 (Web Text))

Max Activating Token Index: 248