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

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

Neuron 4798 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: 1.4757. Min Range: -1.4757

Max Act: 1.4757. Min Act: -0.0002

Data Index: 241269 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.4555. Min Act: -0.0002

Data Index: 7894 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.3914. Min Act: -0.0002

Data Index: 102336 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.3297. Min Act: -0.0002

Data Index: 8625 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.3213. Min Act: -0.0002

Data Index: 11791 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.3145. Min Act: -0.0002

Data Index: 1039543 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2631. Min Act: -0.0002

Data Index: 633369 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2716. Min Act: -0.0002

Data Index: 209223 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2740. Min Act: -0.0002

Data Index: 361648 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2189. Min Act: -0.0002

Data Index: 292364 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2486. Min Act: -0.0002

Data Index: 946775 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2106. Min Act: -0.0002

Data Index: 1124589 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2032. Min Act: -0.0002

Data Index: 8555 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2167. Min Act: -0.0002

Data Index: 1232954 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.1935. Min Act: -0.0002

Data Index: 980496 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.1749. Min Act: -0.0002

Data Index: 345467 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.1630. Min Act: -0.0002

Data Index: 499235 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.1618. Min Act: -0.0002

Data Index: 35677 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.1414. Min Act: -0.0002

Data Index: 223508 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.1203. Min Act: -0.0002

Data Index: 393868 (C4 (Web Text))

Max Activating Token Index: 305