Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2672 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0544. Min Range: -1.0544

Max Act: 1.0544. Min Act: -0.0000

Data Index: 75341 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8737. Min Act: -0.0000

Data Index: 878411 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8360. Min Act: -0.0000

Data Index: 543400 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1151717 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8394. Min Act: -0.0000

Data Index: 681968 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8042. Min Act: -0.0000

Data Index: 662711 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1011990 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1344219 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8005. Min Act: -0.0000

Data Index: 634215 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1224905 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7757. Min Act: -0.0000

Data Index: 512051 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1108268 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7744. Min Act: -0.0000

Data Index: 956020 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7471. Min Act: -0.0000

Data Index: 46573 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7506. Min Act: -0.0000

Data Index: 604371 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.6965. Min Act: -0.0000

Data Index: 297151 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7129. Min Act: -0.0000

Data Index: 581685 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.6409. Min Act: -0.0000

Data Index: 774226 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1147742 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1282564 (C4 (Web Text))

Max Activating Token Index: 626