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

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

Neuron 1058 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0109. Min Range: -1.0109

Max Act: 1.0109. Min Act: -0.0000

Data Index: 468004 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1430476 (Python Code)

Max Activating Token Index: 601

Text #2

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1379096 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1437365 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1360598 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8609. Min Act: -0.0000

Data Index: 161188 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.9001. Min Act: -0.0000

Data Index: 934641 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1554124 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8069. Min Act: -0.0000

Data Index: 47144 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1268906 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8004. Min Act: -0.0000

Data Index: 594467 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8681. Min Act: -0.0000

Data Index: 345420 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7052. Min Act: -0.0000

Data Index: 959470 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1325111 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7718. Min Act: -0.0000

Data Index: 207026 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1271826 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7942. Min Act: -0.0000

Data Index: 916588 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7273. Min Act: -0.0000

Data Index: 235775 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1461362 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.6657. Min Act: -0.0000

Data Index: 462532 (C4 (Web Text))

Max Activating Token Index: 36