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

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

Neuron 3742 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6869. Min Act: -0.0000

Data Index: 235146 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.7097. Min Act: -0.0000

Data Index: 581595 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6508. Min Act: -0.0000

Data Index: 848033 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6780. Min Act: -0.0000

Data Index: 85759 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6851. Min Act: -0.0000

Data Index: 289997 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6926. Min Act: -0.0000

Data Index: 610674 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6450. Min Act: -0.0000

Data Index: 180497 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6685. Min Act: -0.0000

Data Index: 429132 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6764. Min Act: -0.0000

Data Index: 381626 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1209817 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6634. Min Act: -0.0000

Data Index: 638302 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1055665 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6139. Min Act: -0.0000

Data Index: 477732 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6264. Min Act: -0.0000

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6207. Min Act: -0.0000

Data Index: 607590 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1367200 (Python Code)

Max Activating Token Index: 757

Text #16

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6319. Min Act: -0.0000

Data Index: 957024 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.6087. Min Act: -0.0000

Data Index: 2103 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1300573 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1317085 (C4 (Web Text))

Max Activating Token Index: 942