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

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

Neuron 270 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.2962. Min Act: -0.0002

Data Index: 929545 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.3003. Min Act: -0.0002

Data Index: 436787 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.2547. Min Act: -0.0003

Data Index: 276346 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.2505. Min Act: -0.0002

Data Index: 1006288 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.2132. Min Act: -0.0002

Data Index: 137163 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1942. Min Act: -0.0002

Data Index: 808537 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1837. Min Act: -0.0002

Data Index: 694150 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1579. Min Act: -0.0002

Data Index: 737064 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1599. Min Act: -0.0002

Data Index: 1156802 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1483. Min Act: -0.0003

Data Index: 381187 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1640. Min Act: -0.0002

Data Index: 73169 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1554. Min Act: -0.0002

Data Index: 439282 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1338. Min Act: -0.0002

Data Index: 31944 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1321. Min Act: -0.0002

Data Index: 961764 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1111. Min Act: -0.0002

Data Index: 351040 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0984. Min Act: -0.0002

Data Index: 63946 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0957. Min Act: -0.0003

Data Index: 1015292 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1022. Min Act: -0.0002

Data Index: 1147587 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0897. Min Act: -0.0002

Data Index: 170111 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0920. Min Act: -0.0002

Data Index: 785450 (C4 (Web Text))

Max Activating Token Index: 159