Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1397 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0561. Min Act: -0.0003

Data Index: 226663 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0566. Min Act: -0.0003

Data Index: 595832 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0522. Min Act: -0.0003

Data Index: 270943 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0519. Min Act: -0.0003

Data Index: 719999 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1195790 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0501. Min Act: -0.0003

Data Index: 145226 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0504. Min Act: -0.0003

Data Index: 794292 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0462. Min Act: -0.0003

Data Index: 369010 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0490. Min Act: -0.0003

Data Index: 841799 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0462. Min Act: -0.0003

Data Index: 602115 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0431. Min Act: -0.0003

Data Index: 76851 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1295497 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1053525 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1090113 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0445. Min Act: -0.0003

Data Index: 80630 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0451. Min Act: -0.0003

Data Index: 243171 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0437. Min Act: -0.0003

Data Index: 815948 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1135495 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0439. Min Act: -0.0003

Data Index: 614535 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1083999 (C4 (Web Text))

Max Activating Token Index: 553