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

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

Neuron 5921 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: 5.3462. Min Range: -5.3462

Max Act: 5.2253. Min Act: -0.0000

Data Index: 1107350 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.3462. Min Act: -0.0000

Data Index: 496419 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.2651. Min Act: -0.0000

Data Index: 492711 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.0891. Min Act: -0.0000

Data Index: 1178025 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.2838. Min Act: -0.0000

Data Index: 1343773 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.2440. Min Act: -0.0000

Data Index: 1331687 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1520. Min Act: -0.0000

Data Index: 712865 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1504. Min Act: -0.0000

Data Index: 878925 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 5.3462. Min Range: -5.3462

Max Act: 4.9449. Min Act: -0.0000

Data Index: 1224604 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.0900. Min Act: -0.0000

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.1066. Min Act: -0.0000

Data Index: 485296 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 5.3462. Min Range: -5.3462

Max Act: 4.9033. Min Act: -0.0000

Data Index: 1269416 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.0939. Min Act: -0.0000

Data Index: 524913 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.0628. Min Act: -0.0000

Data Index: 496186 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.0590. Min Act: -0.0000

Data Index: 383806 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 5.3462. Min Range: -5.3462

Max Act: 4.8571. Min Act: -0.0000

Data Index: 208852 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 5.3462. Min Range: -5.3462

Max Act: 5.0522. Min Act: -0.0000

Data Index: 1340998 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 5.3462. Min Range: -5.3462

Max Act: 4.8411. Min Act: -0.0000

Data Index: 1288681 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 5.3462. Min Range: -5.3462

Max Act: 4.8157. Min Act: -0.0000

Data Index: 305113 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 5.3462. Min Range: -5.3462

Max Act: 4.9341. Min Act: -0.0000

Data Index: 408836 (C4 (Web Text))

Max Activating Token Index: 996