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

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

Neuron 5434 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.1029. Min Range: -7.1029

Max Act: 7.1029. Min Act: -0.0000

Data Index: 1484962 (Python Code)

Max Activating Token Index: 669

Text #1

Max Range: 7.1029. Min Range: -7.1029

Max Act: 6.2641. Min Act: -0.0000

Data Index: 1392169 (Python Code)

Max Activating Token Index: 1003

Text #2

Max Range: 7.1029. Min Range: -7.1029

Max Act: 6.2141. Min Act: -0.0000

Data Index: 1614467 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 7.1029. Min Range: -7.1029

Max Act: 6.0898. Min Act: -0.0000

Data Index: 1401975 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.5158. Min Act: -0.0000

Data Index: 1484813 (Python Code)

Max Activating Token Index: 224

Text #5

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.8372. Min Act: -0.0000

Data Index: 1428290 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 7.1029. Min Range: -7.1029

Max Act: 6.0065. Min Act: -0.0000

Data Index: 1457414 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.6909. Min Act: -0.0000

Data Index: 453297 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.4919. Min Act: -0.0000

Data Index: 823792 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.8718. Min Act: -0.0000

Data Index: 1241181 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.6438. Min Act: -0.0000

Data Index: 1444377 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.4337. Min Act: -0.0000

Data Index: 801990 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.5650. Min Act: -0.0000

Data Index: 1395269 (Python Code)

Max Activating Token Index: 348

Text #13

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.7341. Min Act: -0.0000

Data Index: 1370069 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.3231. Min Act: -0.0000

Data Index: 1626779 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.4710. Min Act: -0.0000

Data Index: 1500853 (Python Code)

Max Activating Token Index: 917

Text #16

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.4647. Min Act: -0.0000

Data Index: 1401373 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.4476. Min Act: -0.0000

Data Index: 1448379 (Python Code)

Max Activating Token Index: 538

Text #18

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.4152. Min Act: -0.0000

Data Index: 1442269 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 7.1029. Min Range: -7.1029

Max Act: 5.6040. Min Act: -0.0000

Data Index: 317219 (C4 (Web Text))

Max Activating Token Index: 50