Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1458 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.3096. Min Act: -0.0000

Data Index: 41673 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1368050 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9874. Min Act: -0.0000

Data Index: 344317 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1548169 (Python Code)

Max Activating Token Index: 590

Text #4

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.0937. Min Act: -0.0000

Data Index: 101823 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9889. Min Act: -0.0000

Data Index: 102959 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9096. Min Act: -0.0000

Data Index: 660504 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.8874. Min Act: -0.0000

Data Index: 437843 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1373912 (Python Code)

Max Activating Token Index: 430

Text #9

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.8089. Min Act: -0.0000

Data Index: 177455 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1644178 (Python Code)

Max Activating Token Index: 287

Text #11

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1463420 (Python Code)

Max Activating Token Index: 470

Text #12

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1551087 (Python Code)

Max Activating Token Index: 355

Text #13

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1402649 (Python Code)

Max Activating Token Index: 97

Text #14

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1549766 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1400356 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1379140 (Python Code)

Max Activating Token Index: 736

Text #17

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1554772 (Python Code)

Max Activating Token Index: 358

Text #18

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1411106 (Python Code)

Max Activating Token Index: 439

Text #19

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1619286 (Python Code)

Max Activating Token Index: 503