Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3384 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.8172. Min Act: -0.0000

Data Index: 840110 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.1206. Min Act: -0.0000

Data Index: 697455 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.9300. Min Act: -0.0000

Data Index: 1249369 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.4782. Min Act: -0.0000

Data Index: 1254565 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.9897. Min Act: -0.0000

Data Index: 703732 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.9446. Min Act: -0.0000

Data Index: 144094 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.4953. Min Act: -0.0000

Data Index: 335243 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.2381. Min Act: -0.0000

Data Index: 1345199 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.3147. Min Act: -0.0000

Data Index: 503272 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.3074. Min Act: -0.0000

Data Index: 127695 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.3806. Min Act: -0.0000

Data Index: 258113 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 4.8172. Min Range: -4.8172

Max Act: 2.9183. Min Act: -0.0000

Data Index: 931692 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.5642. Min Act: -0.0000

Data Index: 265693 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 4.8172. Min Range: -4.8172

Max Act: 2.8490. Min Act: -0.0000

Data Index: 88695 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.0907. Min Act: -0.0000

Data Index: 385874 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 4.8172. Min Range: -4.8172

Max Act: 2.7754. Min Act: -0.0000

Data Index: 893870 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 4.8172. Min Range: -4.8172

Max Act: 2.7217. Min Act: -0.0000

Data Index: 116506 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 4.8172. Min Range: -4.8172

Max Act: 2.3354. Min Act: -0.0000

Data Index: 954418 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 4.8172. Min Range: -4.8172

Max Act: 2.0492. Min Act: 0.0000

Data Index: 316334 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 4.8172. Min Range: -4.8172

Max Act: 1.9145. Min Act: -0.0000

Data Index: 197746 (C4 (Web Text))

Max Activating Token Index: 327