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

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

Neuron 137 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: 0.7053. Min Range: -0.7053

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1299164 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5511. Min Act: -0.0000

Data Index: 92984 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5535. Min Act: -0.0000

Data Index: 322682 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5478. Min Act: -0.0000

Data Index: 78150 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4771. Min Act: -0.0000

Data Index: 837099 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1322218 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1336577 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4979. Min Act: -0.0000

Data Index: 710164 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5108. Min Act: -0.0000

Data Index: 139080 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5171. Min Act: -0.0000

Data Index: 214072 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4850. Min Act: -0.0000

Data Index: 195005 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4918. Min Act: -0.0000

Data Index: 64434 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1283285 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4779. Min Act: -0.0000

Data Index: 372148 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4768. Min Act: -0.0000

Data Index: 616186 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4889. Min Act: -0.0000

Data Index: 348097 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4362. Min Act: -0.0000

Data Index: 548948 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4212. Min Act: -0.0000

Data Index: 979473 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1178624 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4436. Min Act: -0.0000

Data Index: 80692 (C4 (Web Text))

Max Activating Token Index: 238