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

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

Neuron 3708 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.8626. Min Act: -0.0000

Data Index: 230063 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1129760 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1189956 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.6847. Min Act: -0.0000

Data Index: 392476 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.6575. Min Act: -0.0000

Data Index: 898754 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.6651. Min Act: -0.0000

Data Index: 164363 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.6150. Min Act: -0.0000

Data Index: 941937 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5783. Min Act: -0.0000

Data Index: 970095 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1126591 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5527. Min Act: -0.0000

Data Index: 800228 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5507. Min Act: -0.0000

Data Index: 824854 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5088. Min Act: -0.0000

Data Index: 564137 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5378. Min Act: -0.0000

Data Index: 831544 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1084989 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5139. Min Act: -0.0000

Data Index: 631982 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.4264. Min Act: -0.0000

Data Index: 702894 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1056772 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.4869. Min Act: -0.0000

Data Index: 615109 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5179. Min Act: -0.0000

Data Index: 662698 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.8626. Min Range: -0.8626

Max Act: 0.5170. Min Act: -0.0000

Data Index: 961002 (C4 (Web Text))

Max Activating Token Index: 40