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

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

Neuron 4806 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: 1.8052. Min Range: -1.8052

Max Act: 1.8052. Min Act: -0.0002

Data Index: 509031 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.6416. Min Act: -0.0002

Data Index: 1010889 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.6459. Min Act: -0.0002

Data Index: 19859 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5495. Min Act: -0.0002

Data Index: 161474 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5760. Min Act: -0.0002

Data Index: 336075 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5474. Min Act: -0.0002

Data Index: 861714 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5701. Min Act: -0.0002

Data Index: 433974 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5597. Min Act: -0.0002

Data Index: 296265 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5152. Min Act: -0.0002

Data Index: 247119 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5106. Min Act: -0.0002

Data Index: 57433 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5065. Min Act: -0.0002

Data Index: 1294755 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5180. Min Act: -0.0002

Data Index: 1151436 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.4877. Min Act: -0.0002

Data Index: 62434 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.4912. Min Act: -0.0002

Data Index: 225691 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.4757. Min Act: -0.0002

Data Index: 73451 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5342. Min Act: -0.0002

Data Index: 1066151 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5130. Min Act: -0.0002

Data Index: 1310208 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5036. Min Act: -0.0002

Data Index: 61935 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.5225. Min Act: -0.0002

Data Index: 1108821 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.8052. Min Range: -1.8052

Max Act: 1.4995. Min Act: -0.0002

Data Index: 574261 (C4 (Web Text))

Max Activating Token Index: 914