Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1197 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1724720 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7361. Min Act: -0.0000

Data Index: 646068 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5679. Min Act: -0.0000

Data Index: 291405 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6432. Min Act: -0.0000

Data Index: 14244 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1855492 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1256435 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5869. Min Act: -0.0000

Data Index: 843959 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5869. Min Act: -0.0000

Data Index: 672260 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6399. Min Act: -0.0000

Data Index: 444383 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1581255 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1437509 (The Pile)

Max Activating Token Index: 765

Text #11

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1102882 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1170757 (The Pile)

Max Activating Token Index: 620

Text #13

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.4967. Min Act: -0.0000

Data Index: 953678 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1471851 (The Pile)

Max Activating Token Index: 728

Text #15

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.4950. Min Act: -0.0000

Data Index: 387831 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5017. Min Act: -0.0000

Data Index: 570190 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.4781. Min Act: -0.0000

Data Index: 181712 (The Pile)

Max Activating Token Index: 827

Text #18

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.4855. Min Act: -0.0000

Data Index: 895306 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.4963. Min Act: -0.0000

Data Index: 815803 (The Pile)

Max Activating Token Index: 629