Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1782 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5880. Min Act: -0.0003

Data Index: 805302 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5699. Min Act: -0.0003

Data Index: 826032 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5162. Min Act: -0.0003

Data Index: 942771 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5354. Min Act: -0.0003

Data Index: 475368 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5435. Min Act: -0.0003

Data Index: 989590 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5157. Min Act: -0.0003

Data Index: 849065 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5337. Min Act: -0.0003

Data Index: 1237112 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5075. Min Act: -0.0003

Data Index: 1207208 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5239. Min Act: -0.0003

Data Index: 814001 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5087. Min Act: -0.0003

Data Index: 897539 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5199. Min Act: -0.0003

Data Index: 455643 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5211. Min Act: -0.0003

Data Index: 1297060 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5299. Min Act: -0.0003

Data Index: 593671 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5122. Min Act: -0.0003

Data Index: 687232 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5105. Min Act: -0.0003

Data Index: 43077 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4929. Min Act: -0.0003

Data Index: 1325256 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4921. Min Act: -0.0003

Data Index: 344908 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5186. Min Act: -0.0003

Data Index: 1029979 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4864. Min Act: -0.0003

Data Index: 291722 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5223. Min Act: -0.0003

Data Index: 1058819 (C4 (Web Text))

Max Activating Token Index: 907