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

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

Neuron 658 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5591. Min Range: -6.5591

Max Act: 6.2513. Min Act: -0.0000

Data Index: 1020461 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 6.5591. Min Range: -6.5591

Max Act: 6.5591. Min Act: -0.0000

Data Index: 218120 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.6681. Min Act: -0.0000

Data Index: 1242333 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.5662. Min Act: -0.0000

Data Index: 536488 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.5565. Min Act: -0.0000

Data Index: 430866 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.5054. Min Act: -0.0000

Data Index: 442760 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.2299. Min Act: -0.0000

Data Index: 1020853 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.5134. Min Act: -0.0000

Data Index: 526928 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.1201. Min Act: -0.0000

Data Index: 140455 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.4492. Min Act: -0.0000

Data Index: 74370 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.6127. Min Act: -0.0000

Data Index: 607217 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.2199. Min Act: -0.0000

Data Index: 1068248 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.0326. Min Act: -0.0000

Data Index: 678200 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.0889. Min Act: -0.0000

Data Index: 304432 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.0931. Min Act: -0.0000

Data Index: 540704 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.2697. Min Act: -0.0000

Data Index: 318262 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 6.5591. Min Range: -6.5591

Max Act: 4.9139. Min Act: -0.0000

Data Index: 1060402 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 6.5591. Min Range: -6.5591

Max Act: 4.9735. Min Act: -0.0000

Data Index: 435895 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 6.5591. Min Range: -6.5591

Max Act: 4.9682. Min Act: -0.0000

Data Index: 699680 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 6.5591. Min Range: -6.5591

Max Act: 5.3094. Min Act: -0.0000

Data Index: 578864 (C4 (Web Text))

Max Activating Token Index: 114