Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3562 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6559. Min Act: -0.0000

Data Index: 610661 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6358. Min Act: -0.0000

Data Index: 396356 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6569. Min Act: -0.0001

Data Index: 382411 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6020. Min Act: -0.0000

Data Index: 756928 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6031. Min Act: -0.0000

Data Index: 261720 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5803. Min Act: -0.0000

Data Index: 26058 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5620. Min Act: -0.0001

Data Index: 513710 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1245650 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4920. Min Act: -0.0001

Data Index: 1261051 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5209. Min Act: -0.0001

Data Index: 1042051 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5155. Min Act: -0.0001

Data Index: 718789 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5199. Min Act: -0.0000

Data Index: 225706 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4858. Min Act: -0.0001

Data Index: 588132 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5303. Min Act: -0.0001

Data Index: 41909 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5033. Min Act: -0.0001

Data Index: 41313 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5194. Min Act: -0.0000

Data Index: 820360 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5171. Min Act: -0.0001

Data Index: 471779 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4892. Min Act: -0.0001

Data Index: 816565 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5027. Min Act: -0.0000

Data Index: 25303 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4879. Min Act: -0.0001

Data Index: 61775 (C4 (Web Text))

Max Activating Token Index: 303