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

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

Neuron 1826 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1522144 (Python Code)

Max Activating Token Index: 245

Text #1

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1513630 (Python Code)

Max Activating Token Index: 358

Text #2

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1624914 (Python Code)

Max Activating Token Index: 467

Text #3

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1438219 (Python Code)

Max Activating Token Index: 442

Text #4

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1596760 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1476624 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1601492 (Python Code)

Max Activating Token Index: 982

Text #7

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1595195 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1574608 (Python Code)

Max Activating Token Index: 241

Text #9

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1536773 (Python Code)

Max Activating Token Index: 989

Text #10

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1607698 (Python Code)

Max Activating Token Index: 576

Text #11

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1592319 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1572159 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1436748 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1559166 (Python Code)

Max Activating Token Index: 146

Text #15

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1555479 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1486443 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1549140 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1517008 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 0.6165. Min Range: -0.6165

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1603045 (Python Code)

Max Activating Token Index: 633