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

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

Neuron 2902 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7753. Min Act: -0.0000

Data Index: 445366 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1310738 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3739. Min Act: -0.0000

Data Index: 538464 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1196986 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3331. Min Act: -0.0000

Data Index: 702203 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3302. Min Act: -0.0000

Data Index: 415377 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1193429 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1217357 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3041. Min Act: -0.0000

Data Index: 717345 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3113. Min Act: -0.0000

Data Index: 249964 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.2876. Min Act: -0.0000

Data Index: 205309 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1068834 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.2825. Min Act: -0.0000

Data Index: 997920 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3109. Min Act: -0.0000

Data Index: 470340 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1020416 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.3002. Min Act: -0.0000

Data Index: 122946 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.2829. Min Act: -0.0000

Data Index: 308570 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.2801. Min Act: -0.0000

Data Index: 322607 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.2960. Min Act: -0.0000

Data Index: 397481 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.2321. Min Act: -0.0000

Data Index: 733415 (C4 (Web Text))

Max Activating Token Index: 227