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

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

Neuron 3507 in Layer 0

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: 0.6423. Min Range: -0.6423

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1477610 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5222. Min Act: -0.0001

Data Index: 1537027 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4766. Min Act: -0.0001

Data Index: 1495573 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4337. Min Act: -0.0001

Data Index: 1439003 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4154. Min Act: -0.0001

Data Index: 1649583 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4155. Min Act: -0.0001

Data Index: 1458912 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3842. Min Act: -0.0001

Data Index: 1438388 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3835. Min Act: -0.0001

Data Index: 1589850 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1465193 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3508. Min Act: -0.0001

Data Index: 1361126 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3340. Min Act: -0.0001

Data Index: 1569231 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3375. Min Act: -0.0001

Data Index: 1361606 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3332. Min Act: -0.0001

Data Index: 1366134 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3227. Min Act: -0.0001

Data Index: 1438628 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3240. Min Act: -0.0001

Data Index: 1606068 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1453612 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1470144 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3105. Min Act: -0.0001

Data Index: 1528431 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3056. Min Act: -0.0002

Data Index: 1540383 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.3047. Min Act: -0.0001

Data Index: 1374226 (Python Code)

Max Activating Token Index: 1023