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

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

Neuron 2134 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: 0.7009. Min Range: -0.7009

Max Act: 0.7009. Min Act: -0.0002

Data Index: 171282 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.6320. Min Act: -0.0002

Data Index: 416347 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.6367. Min Act: -0.0002

Data Index: 727684 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5943. Min Act: -0.0002

Data Index: 1071008 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5949. Min Act: -0.0002

Data Index: 1337879 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5719. Min Act: -0.0002

Data Index: 5086 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5642. Min Act: -0.0002

Data Index: 127113 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5530. Min Act: -0.0002

Data Index: 1330858 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5645. Min Act: -0.0002

Data Index: 155518 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5602. Min Act: -0.0002

Data Index: 1091104 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5637. Min Act: -0.0002

Data Index: 1265854 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5503. Min Act: -0.0002

Data Index: 1317385 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5522. Min Act: -0.0002

Data Index: 423707 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5614. Min Act: -0.0002

Data Index: 391403 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5417. Min Act: -0.0002

Data Index: 341799 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5481. Min Act: -0.0002

Data Index: 586797 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5451. Min Act: -0.0002

Data Index: 1195073 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5436. Min Act: -0.0002

Data Index: 1063950 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5426. Min Act: -0.0002

Data Index: 882582 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5449. Min Act: -0.0002

Data Index: 884288 (C4 (Web Text))

Max Activating Token Index: 240