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

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

Neuron 1850 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: 0.7852. Min Range: -0.7852

Max Act: 0.7852. Min Act: -0.0003

Data Index: 1288333 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7789. Min Act: -0.0003

Data Index: 1337571 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7345. Min Act: -0.0002

Data Index: 1325490 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7259. Min Act: -0.0003

Data Index: 1101062 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7378. Min Act: -0.0002

Data Index: 185847 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7319. Min Act: -0.0002

Data Index: 1009244 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7131. Min Act: -0.0002

Data Index: 703616 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7166. Min Act: -0.0002

Data Index: 1095598 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7014. Min Act: -0.0002

Data Index: 790448 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7052. Min Act: -0.0002

Data Index: 1310194 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7075. Min Act: -0.0002

Data Index: 843035 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6878. Min Act: -0.0002

Data Index: 622455 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6692. Min Act: -0.0002

Data Index: 560834 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6774. Min Act: -0.0002

Data Index: 172875 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6796. Min Act: -0.0002

Data Index: 735448 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6768. Min Act: -0.0002

Data Index: 698097 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6748. Min Act: -0.0002

Data Index: 356441 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6705. Min Act: -0.0002

Data Index: 45059 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6644. Min Act: -0.0002

Data Index: 848977 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6599. Min Act: -0.0002

Data Index: 40635 (C4 (Web Text))

Max Activating Token Index: 521