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

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

Neuron 5900 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: 2.7827. Min Range: -2.7827

Max Act: 2.7593. Min Act: -0.0000

Data Index: 899323 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.6036. Min Act: -0.0000

Data Index: 1300341 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.7581. Min Act: -0.0000

Data Index: 837115 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.7827. Min Act: -0.0000

Data Index: 230042 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.7205. Min Act: -0.0000

Data Index: 942841 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.4538. Min Act: -0.0000

Data Index: 991095 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.3501. Min Act: -0.0000

Data Index: 990789 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.3224. Min Act: -0.0000

Data Index: 97059 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.3183. Min Act: -0.0000

Data Index: 1169755 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0791. Min Act: -0.0000

Data Index: 1321477 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.3125. Min Act: -0.0000

Data Index: 798275 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.5544. Min Act: -0.0000

Data Index: 1063177 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.3764. Min Act: -0.0000

Data Index: 396260 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.1244. Min Act: -0.0000

Data Index: 310272 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.2026. Min Act: -0.0000

Data Index: 1250732 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.1943. Min Act: -0.0000

Data Index: 194850 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 2.7827. Min Range: -2.7827

Max Act: 1.9743. Min Act: -0.0000

Data Index: 489606 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0528. Min Act: -0.0000

Data Index: 415220 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.2726. Min Act: -0.0000

Data Index: 229164 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 2.7827. Min Range: -2.7827

Max Act: 1.8153. Min Act: -0.0000

Data Index: 932298 (C4 (Web Text))

Max Activating Token Index: 373