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

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

Neuron 5328 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: 2.6291. Min Range: -2.6291

Max Act: 2.6291. Min Act: -0.0000

Data Index: 242605 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 2.6291. Min Range: -2.6291

Max Act: 2.4224. Min Act: -0.0000

Data Index: 772616 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 2.6291. Min Range: -2.6291

Max Act: 2.3840. Min Act: -0.0000

Data Index: 688888 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 2.6291. Min Range: -2.6291

Max Act: 2.3933. Min Act: -0.0000

Data Index: 380537 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 2.6291. Min Range: -2.6291

Max Act: 2.0995. Min Act: -0.0000

Data Index: 244551 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 2.6291. Min Range: -2.6291

Max Act: 2.2232. Min Act: -0.0000

Data Index: 100108 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 2.6291. Min Range: -2.6291

Max Act: 2.4156. Min Act: -0.0000

Data Index: 1340190 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.9844. Min Act: -0.0000

Data Index: 1177484 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 2.6291. Min Range: -2.6291

Max Act: 2.0737. Min Act: -0.0000

Data Index: 133002 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 2.6291. Min Range: -2.6291

Max Act: 2.1165. Min Act: -0.0000

Data Index: 1284102 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.9625. Min Act: -0.0000

Data Index: 254488 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.9542. Min Act: -0.0000

Data Index: 200436 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.9488. Min Act: -0.0000

Data Index: 46080 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.8112. Min Act: -0.0000

Data Index: 497022 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 2.6291. Min Range: -2.6291

Max Act: 2.0129. Min Act: -0.0000

Data Index: 259827 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.7975. Min Act: -0.0000

Data Index: 906811 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.7854. Min Act: -0.0000

Data Index: 673561 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.8867. Min Act: -0.0000

Data Index: 1088309 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.7635. Min Act: -0.0000

Data Index: 534412 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 2.6291. Min Range: -2.6291

Max Act: 1.8488. Min Act: -0.0000

Data Index: 470863 (C4 (Web Text))

Max Activating Token Index: 669