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

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

Neuron 2925 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: 5.4162. Min Range: -5.4162

Max Act: 5.4162. Min Act: -0.0000

Data Index: 186189 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 5.4162. Min Range: -5.4162

Max Act: 5.1402. Min Act: -0.0000

Data Index: 1616291 (Python Code)

Max Activating Token Index: 146

Text #2

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.9649. Min Act: -0.0000

Data Index: 1564092 (Python Code)

Max Activating Token Index: 69

Text #3

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.5432. Min Act: -0.0000

Data Index: 672825 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.7071. Min Act: -0.0000

Data Index: 275165 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.6370. Min Act: -0.0000

Data Index: 443578 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.3891. Min Act: -0.0000

Data Index: 779391 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.4671. Min Act: -0.0000

Data Index: 58818 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.2599. Min Act: -0.0000

Data Index: 246701 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.2302. Min Act: -0.0000

Data Index: 668716 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.1553. Min Act: -0.0000

Data Index: 1559713 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.5875. Min Act: -0.0000

Data Index: 146335 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 5.4162. Min Range: -5.4162

Max Act: 3.9059. Min Act: -0.0000

Data Index: 715059 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.2285. Min Act: -0.0000

Data Index: 286006 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 5.4162. Min Range: -5.4162

Max Act: 3.7188. Min Act: -0.0000

Data Index: 1629638 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.1460. Min Act: -0.0000

Data Index: 1594446 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.0082. Min Act: -0.0000

Data Index: 847699 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 5.4162. Min Range: -5.4162

Max Act: 3.8228. Min Act: -0.0000

Data Index: 451128 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 5.4162. Min Range: -5.4162

Max Act: 3.9706. Min Act: -0.0000

Data Index: 629807 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 5.4162. Min Range: -5.4162

Max Act: 4.1921. Min Act: -0.0000

Data Index: 471735 (C4 (Web Text))

Max Activating Token Index: 225