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

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

Neuron 2777 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3421. Min Range: -4.3421

Max Act: 4.0270. Min Act: -0.0001

Data Index: 24376 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 4.3421. Min Range: -4.3421

Max Act: 4.3421. Min Act: -0.0000

Data Index: 1019348 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.9206. Min Act: -0.0001

Data Index: 1294294 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.8135. Min Act: -0.0000

Data Index: 633111 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.7867. Min Act: -0.0000

Data Index: 104697 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.6448. Min Act: -0.0000

Data Index: 308871 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.5770. Min Act: -0.0000

Data Index: 342174 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.3176. Min Act: -0.0000

Data Index: 1144328 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.5840. Min Act: -0.0000

Data Index: 1100589 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.3877. Min Act: -0.0000

Data Index: 1250071 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.3545. Min Act: -0.0000

Data Index: 1318075 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.3789. Min Act: -0.0000

Data Index: 1321303 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.3193. Min Act: -0.0001

Data Index: 380294 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.1723. Min Act: -0.0000

Data Index: 878927 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.1785. Min Act: -0.0000

Data Index: 807947 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.1450. Min Act: -0.0001

Data Index: 791657 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.0102. Min Act: -0.0001

Data Index: 726519 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.4162. Min Act: -0.0000

Data Index: 593599 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.1480. Min Act: -0.0001

Data Index: 1094589 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 4.3421. Min Range: -4.3421

Max Act: 3.2464. Min Act: -0.0000

Data Index: 1205736 (C4 (Web Text))

Max Activating Token Index: 829