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

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

Neuron 2147 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0788. Min Range: -2.0788

Max Act: 2.0788. Min Act: -0.0000

Data Index: 362067 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.9649. Min Act: -0.0000

Data Index: 308245 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.8933. Min Act: -0.0000

Data Index: 864922 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.8655. Min Act: -0.0000

Data Index: 728331 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.7518. Min Act: -0.0000

Data Index: 829560 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.8347. Min Act: -0.0000

Data Index: 239326 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.8186. Min Act: -0.0000

Data Index: 653098 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.7095. Min Act: -0.0000

Data Index: 932946 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.6046. Min Act: -0.0000

Data Index: 768158 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.7753. Min Act: -0.0000

Data Index: 548871 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.8712. Min Act: -0.0000

Data Index: 1291717 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.7525. Min Act: -0.0000

Data Index: 821666 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.7501. Min Act: -0.0000

Data Index: 819687 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.8613. Min Act: -0.0000

Data Index: 877900 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.7237. Min Act: -0.0000

Data Index: 1228564 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.7306. Min Act: -0.0000

Data Index: 73348 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.7018. Min Act: -0.0000

Data Index: 756091 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.6950. Min Act: -0.0000

Data Index: 1345038 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.6970. Min Act: -0.0000

Data Index: 408450 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 2.0788. Min Range: -2.0788

Max Act: 1.5894. Min Act: -0.0000

Data Index: 453695 (C4 (Web Text))

Max Activating Token Index: 892