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

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

Neuron 2294 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.2439. Min Act: -0.0000

Data Index: 239978 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1196483 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1892. Min Act: 0.0000

Data Index: 1275707 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1268586 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0191. Min Act: -0.0000

Data Index: 316234 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.9132. Min Act: -0.0000

Data Index: 380012 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.9059. Min Act: 0.0001

Data Index: 342431 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8417. Min Act: -0.0000

Data Index: 241343 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8504. Min Act: -0.0000

Data Index: 97140 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8396. Min Act: -0.0000

Data Index: 716027 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8349. Min Act: -0.0000

Data Index: 769856 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8754. Min Act: -0.0000

Data Index: 817110 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8009. Min Act: -0.0000

Data Index: 61489 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8442. Min Act: -0.0000

Data Index: 668086 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1196195 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1055744 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.7713. Min Act: -0.0000

Data Index: 938037 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.7652. Min Act: -0.0000

Data Index: 552008 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.7699. Min Act: -0.0000

Data Index: 705377 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 1.2439. Min Range: -1.2439

Max Act: 0.8162. Min Act: 0.0000

Data Index: 800164 (C4 (Web Text))

Max Activating Token Index: 628