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

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

Neuron 3160 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: 2.5543. Min Range: -2.5543

Max Act: 2.5543. Min Act: -0.0000

Data Index: 575939 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.5465. Min Act: -0.0000

Data Index: 371681 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.4387. Min Act: -0.0000

Data Index: 297088 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.4234. Min Act: -0.0000

Data Index: 864621 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.3441. Min Act: -0.0000

Data Index: 1118606 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.1961. Min Act: -0.0000

Data Index: 1273169 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.3944. Min Act: -0.0000

Data Index: 698105 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.2237. Min Act: -0.0000

Data Index: 104056 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.0752. Min Act: -0.0000

Data Index: 987145 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.0312. Min Act: -0.0000

Data Index: 607530 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.2471. Min Act: -0.0000

Data Index: 72615 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 2.5543. Min Range: -2.5543

Max Act: 2.0157. Min Act: -0.0000

Data Index: 70316 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 2.5543. Min Range: -2.5543

Max Act: 1.8415. Min Act: -0.0000

Data Index: 1133312 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 2.5543. Min Range: -2.5543

Max Act: 1.8076. Min Act: -0.0000

Data Index: 764444 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 2.5543. Min Range: -2.5543

Max Act: 1.7776. Min Act: -0.0000

Data Index: 8287 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 2.5543. Min Range: -2.5543

Max Act: 1.5431. Min Act: -0.0000

Data Index: 707604 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 2.5543. Min Range: -2.5543

Max Act: 1.4562. Min Act: -0.0000

Data Index: 148878 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 2.5543. Min Range: -2.5543

Max Act: 1.9512. Min Act: -0.0000

Data Index: 1132201 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 2.5543. Min Range: -2.5543

Max Act: 1.6064. Min Act: -0.0000

Data Index: 893671 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 2.5543. Min Range: -2.5543

Max Act: 1.4493. Min Act: -0.0000

Data Index: 909674 (C4 (Web Text))

Max Activating Token Index: 223