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

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

Neuron 3602 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: 0.4384. Min Range: -0.4384

Max Act: 0.4384. Min Act: -0.0002

Data Index: 1365555 (Python Code)

Max Activating Token Index: 266

Text #1

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4373. Min Act: -0.0002

Data Index: 1363374 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4375. Min Act: -0.0002

Data Index: 1546133 (Python Code)

Max Activating Token Index: 207

Text #3

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4276. Min Act: -0.0002

Data Index: 1455678 (Python Code)

Max Activating Token Index: 214

Text #4

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4173. Min Act: -0.0002

Data Index: 1647086 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4157. Min Act: -0.0002

Data Index: 354959 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4220. Min Act: -0.0002

Data Index: 1636928 (Python Code)

Max Activating Token Index: 260

Text #7

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4232. Min Act: -0.0002

Data Index: 1397755 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4134. Min Act: -0.0002

Data Index: 1451416 (Python Code)

Max Activating Token Index: 755

Text #9

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4170. Min Act: -0.0002

Data Index: 1431954 (Python Code)

Max Activating Token Index: 102

Text #10

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4210. Min Act: -0.0002

Data Index: 147536 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4133. Min Act: -0.0002

Data Index: 782300 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4105. Min Act: -0.0002

Data Index: 1402222 (Python Code)

Max Activating Token Index: 844

Text #13

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4146. Min Act: -0.0002

Data Index: 278775 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4033. Min Act: -0.0002

Data Index: 1534994 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4019. Min Act: -0.0002

Data Index: 1377613 (Python Code)

Max Activating Token Index: 270

Text #16

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4047. Min Act: -0.0002

Data Index: 1465506 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4031. Min Act: -0.0002

Data Index: 1400561 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4098. Min Act: -0.0002

Data Index: 1529228 (Python Code)

Max Activating Token Index: 181

Text #19

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4166. Min Act: -0.0002

Data Index: 1255868 (C4 (Web Text))

Max Activating Token Index: 873