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

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

Neuron 5708 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2576. Min Range: -6.2576

Max Act: 6.2576. Min Act: -0.0000

Data Index: 430124 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 6.2576. Min Range: -6.2576

Max Act: 5.6320. Min Act: -0.0000

Data Index: 761176 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 6.2576. Min Range: -6.2576

Max Act: 5.5991. Min Act: -0.0000

Data Index: 753978 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 6.2576. Min Range: -6.2576

Max Act: 5.4958. Min Act: -0.0000

Data Index: 289284 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 6.2576. Min Range: -6.2576

Max Act: 5.1998. Min Act: -0.0000

Data Index: 240452 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.8536. Min Act: -0.0000

Data Index: 1063543 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 6.2576. Min Range: -6.2576

Max Act: 5.4460. Min Act: -0.0000

Data Index: 289086 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.8028. Min Act: -0.0000

Data Index: 104424 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.3512. Min Act: -0.0000

Data Index: 1044741 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.7930. Min Act: -0.0000

Data Index: 1056044 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.7848. Min Act: -0.0000

Data Index: 572447 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.5413. Min Act: -0.0000

Data Index: 326611 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.8822. Min Act: -0.0000

Data Index: 745376 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.6657. Min Act: -0.0000

Data Index: 509889 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 6.2576. Min Range: -6.2576

Max Act: 5.1032. Min Act: -0.0000

Data Index: 1090857 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.6386. Min Act: -0.0000

Data Index: 1342119 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.2843. Min Act: -0.0000

Data Index: 371499 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.5797. Min Act: -0.0000

Data Index: 4891 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.7569. Min Act: -0.0000

Data Index: 601617 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 6.2576. Min Range: -6.2576

Max Act: 4.5312. Min Act: -0.0000

Data Index: 71610 (C4 (Web Text))

Max Activating Token Index: 660