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

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

Neuron 604 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: 0.5587. Min Range: -0.5587

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1532209 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1516633 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.3688. Min Act: -0.0001

Data Index: 1403301 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.3071. Min Act: -0.0001

Data Index: 1615972 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1601986 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2578. Min Act: -0.0001

Data Index: 1413048 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2366. Min Act: -0.0001

Data Index: 1479363 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1607570 (Python Code)

Max Activating Token Index: 364

Text #8

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2285. Min Act: -0.0001

Data Index: 1576739 (Python Code)

Max Activating Token Index: 870

Text #9

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1383263 (Python Code)

Max Activating Token Index: 729

Text #10

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1364540 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2119. Min Act: -0.0001

Data Index: 1380971 (Python Code)

Max Activating Token Index: 201

Text #12

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1292700 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2099. Min Act: -0.0001

Data Index: 1536399 (Python Code)

Max Activating Token Index: 991

Text #14

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1592277 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1038037 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2068. Min Act: -0.0001

Data Index: 1429407 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1401921 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1603051 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1567423 (Python Code)

Max Activating Token Index: 781