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

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

Neuron 159 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.8766. Min Act: -0.0000

Data Index: 1129585 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.1504. Min Act: -0.0000

Data Index: 813247 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.2467. Min Act: -0.0000

Data Index: 2455 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.0966. Min Act: -0.0001

Data Index: 118901 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.1366. Min Act: -0.0001

Data Index: 1116248 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.9648. Min Act: -0.0001

Data Index: 1245581 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.9916. Min Act: -0.0000

Data Index: 707661 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.0355. Min Act: -0.0001

Data Index: 746992 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1158124 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1112338 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.9632. Min Act: -0.0000

Data Index: 714540 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1330419 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.9925. Min Act: -0.0000

Data Index: 336436 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.9313. Min Act: -0.0000

Data Index: 908464 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.8575. Min Act: -0.0001

Data Index: 528221 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1073127 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1143252 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.8867. Min Act: -0.0001

Data Index: 907218 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.8171. Min Act: -0.0000

Data Index: 617672 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 1.8766. Min Range: -1.8766

Max Act: 0.8009. Min Act: -0.0001

Data Index: 465456 (C4 (Web Text))

Max Activating Token Index: 660